Description:FIELD OF INVENTION
[0001] Embodiments of the present disclosure relate generally to Radar and Surveillance systems
and more specifically to classification of objects in a radar systems.
RELATED ART
[0002] Radar systems are generally employed for object detection, tracking, terrain mapping,
surveillance, traffic management, traffic enforcement etc. As is well known, Radars can detect
surrounding obstacles or objects and determine information like range, velocity and angle of the
object(s) that are in motion or at rest.
[0003] Radar system may transmit a sequence of pulses (as in Pulsed radar systems) or may
transmit a frequency modulated continuous wave signal (as in FMCW radar) and processes the
corresponding signal reflected by objects (reflected signal) to determine one or more parameters
such as range (distance), Doppler (velocity), elevation/azimuth (angles) of one or more objects.
The distance, velocity and angle are referred to as primary information. This primary information
is received per target/point. Often, this primary information is received instantaneously or
accumulated over a period of time and is further processed to group points of similar
characteristics into clusters (group of points). Clusters are tracked over a time interval of one or
several radar frames to turn them into ‘detected objects’ or ‘tracks’. Secondary parameters such as
length, breadth, height radar cross section (RCS), trajectory etc., may be derived for these tracks
every frame or over a span of several frames. Combination of primary and secondary parameters
of detected objects is called as an extended feature set or simply feature set.
[0004] In certain applications, the detected objects are required to be classified into different
classes. For example, in case of traffic enforcement and/or traffic management and/or toll
collection etc., vehicles are required to be classified into certain classes like two-wheeler, light
motor vehicle (LMVs), heavy motor vehicles (HMVs) etc.
[0005] Conventionally, additional sensing modalities such as video cameras, Lidar (light
detection and ranging) technology, etc., are employed in addition to the Radar system to classify
the objects detected by the Radar. In other words, information captured through a sensing
modality other than radar is used to aid in the classification of objects detected by the radar
system. The camera data or additional data assisting the radar system is referred to as the “ground
truth” as is well known in the technology area of neural network/machine learning.

3

[0006] FIG. 1A depicts conventional classification techniques. As shown there, the classifier 130
is shown receiving radar data 113 from the radar system 110 and additional data 123 from the
supplementary system 120. The supplementary system may be a video camera, LiDAR, etc., and
the associated signal processing system. The radar system 110 may include the radar signal
processing electronics/processors with associated feature extraction elements. Accordingly, the
data on path 113 may be one or more of the radar data, extended feature set, etc. The data on path
123 may be ground truth derived from the system 120. The classifier 130 uses the ground truth
123 to classify the radar data 113 into set of classes and provide the classified radar data on path
139.
[0007] One conventional object classification technique is more fully described in a literature
titled “A Novel Neural Network for Enhanced Automotive Radar Object Recognition, authored
by Xiangyu Gao, Guanbin Xing, and published in IEEE Sensor Journal, 2020, Volume: 21, Issue:
4, dated 15 February 2021. In this approach, time-synchronized Radar and Camera data are
collected for preparing a training dataset. The radar data collected is used to obtain "heat maps",
which are usually range-azimuth angle, range-velocity or velocity-angle. These maps are then fed
to Convolutional Auto-encoders with the true class supplied by the camera images. The
convolutional auto-encoders learn the features of each class with the time-synchronized training
data of radar feature set and the true classes, during the training phase. The features from all the
encoders are fused in a fusion module, and the classification is done by a convolution neural
network (CNN) taking fused features as an input.
[0008] FIG. 1B provides the operation of such conventional system. As shown there, the radar
system 140 is shown providing raw radar data. The 3D FFT unit 151, range-Doppler-angle
heatmap 152 together operates as radar data processor and provides the processed radar data
(here, the Heatmaps as features) to the classifier that is CNN160. The CNN 160 is shown
receiving the ground truth from the camera system 165 to help the CNN learn features of various
classes via supervised learning.
[0009] Similarly, another conventional object classification technique is more fully described in a
literature titled “Vehicle Classification Based on Convolution Networks Applied to FMCW Radar
Signals”, authored by Samuele Capobianco, Luca Facheris, Fabrizio Cuccoli & Simone Marinai.
In that, briefly, the FMCW Radar produces a chirp signal that reflects off the target. The signal
thus obtained is a one dimensional (1D) temporal signal. A Short Time Fourier Transform

4

(STFT) is performed on the signal by splitting it into smaller moving windows to produce three
2D Range Doppler signatures like up ramp, down ramp and average ramp. The dataset used to
train the Neural Network (called DeepRadarNet) contains several training examples for different
kind of vehicles, where the true labels are provided by a human that operates as ground truth. FIG.
1C provides the operation of such conventional system. As shown there, the radar system 170 is
shown providing raw radar data. The STFT unit 181 and stacker 182 together operate to generate
range Doppler images and 3D tensor. The DeepRadarNet 190 is operative as classifier is shown to
receive the tensors from the unit 182 and the Groundtruth 195 through manual entry.
[0010] Apparently, in the conventional systems, additional data derived from supplementary
sensing modality/modalities (other than radar) is first given class-label and the same is employed
as training examples for a machine attempting to learn the radar feature set corresponding to the
given class-labels – a process typically termed as supervised learning. In general, large data sets
are required to be captured and employed in the training phase for machine learning as a starting
point for real time operations. Such classifications are inefficient at least when the operating
conditions are not known beforehand. That apart, the data in the real time operation may be
different from that of the training phase due to operating temperature and installation conditions,
device-to-device variations, classes of objects to be encountered, etc., thus, rendering the
conventional classification techniques inefficient in many applications. Further, the conventional
techniques require strict supervision for training and are not capable of operating autonomously or
in a plug-and-play manner. The conventional radar classifiers are not adjustable or alterable
online based on operating condition. The conventional systems are computationally intensive to
build and train and are therefore are expensive. For example the CNN may require hundreds of
GB (gigabytes) of data to train the classifier.**
SUMMARY
[0011] According to an aspect, a radar system comprising a transmitter transmitting a radar
signal, a receiver receiving a reflected signal that is a reflection of the radar signal from a
plurality of objects, in that the receiver is configured generate a point cloud comprising plurality
of points with each point representing a range, a velocity and a position information, a feature
extension unit configured to generate a plurality of tracks from the point cloud with each track
comprising a corresponding set of points and generating an extended feature set for each track, in
that each track representing an object in the plurality of objects and a classifier classifying the

5

plurality of tracks into a set of classes using a reference data derived from the range, the velocity,
the position information and the extended features.
[0012] According to another aspect, a method of classifying a plurality of detected objects in a
radar system comprising collecting radar data over multiple numbers of frames, arranging
collected data over multiple dimensions, detecting a plurality of tracks representing the plurality
of objects, forming clusters over selected dimensions, tracking each track over the multiple
frames, identifying and selecting a centroid Data for each cluster, reinforcing the centroid data,
comparing reinforced data with a preset threshold value, provide reinforced data as reference for
classification when the comparison result is positive and classifying the tracks based on the
reference.
[0013] Several aspects are described below, with reference to diagrams. It should be understood
that numerous specific details, relationships, and methods are set forth to provide a full
understanding of the present disclosure. One who skilled in the relevant art, however, will readily
recognize that the present disclosure may be practiced without one or more of the specific details,
or with other methods, etc. In other instances, well-known structures or operations are not shown
in detail to avoid obscuring the features of the present disclosure.
BRIEF DESCRIPTION OF DRAWINGS
[0014] FIG. 1A depicts conventional classification techniques.
[0015] FIG. 1B provides the operation of one conventional system.
[0016] FIG. 1C provides the operation of another conventional system.
[0017] FIG. 2 is a block diagram of an example radar system in which various aspects of the
present invention may be seen.
[0018] FIG. 3 is an example radar transceiver for object detection and recognition in an
embodiment.
[0019] FIG. 4A illustrates example point cloud in one embodiment.
[0020] FIG. 4B is a table illustrating primary radar data.
[0021] FIG. 5A is a block diagram illustrating the manner in which the feature extraction block
and the object classifier may be implemented in an embodiment.
[0022] FIG. 5B is a table illustrating example multi-dimensional clusters.
[0023] FIG. 6 is a block diagram illustrating the generation of training data in one embodiment.

6

[0024] FIG. 7A illustrating the data points arranged in the selected two dimensions of RCS on X-
Axis and Width on Y axis.

[0025] FIG. 7B illustrating the data points arranged in the selected two dimensions of RCS on X-
Axis and Velocity on Y axis

[0026] FIG. 7C illustrating the data points arranged in the selected two dimensions of height on
X- Axis and width on Y axis
[0027] FIG. 8 illustrates the manner in which the cluster is formed in an embodiment.
[0028] FIG. 9 is a graph illustrating the manner in which the data points are reinforced.
DETAILED DESCRIPTION OF THE PREFERRED EXAMPLES
[0029] FIG. 2 is a block diagram of an example radar system 200 (environment) in which various
aspects of the present invention may be seen. The environment is shown comprising objects 210,
Radio Frequency (RF) transceiver 220, processor 230, output device 240 and memory 250. Each
element in the system 200 is further described below.
[0030] RF transceiver 220 transmits a radar (RF) signal over a desired direction(s) and receives a
reflected radar signal that is reflected by the objects 210. In one embodiment, the RF transceiver
220 may employ multiple (one or more) receiving antennas to receive the reflected RF signal and
multiple (one or more) transmitting antenna for transmitting the radar signal. Accordingly, the
transceiver 220 may employ these multiple transmitting/receiving antennas in several of multiple
input and multiple output (MIMO) configurations to form desired transmitting and receiving RF
signal beam (often referred to as Beam forming) to detect objects from the reflected signal. The
objects 210 may comprise a terrain, terrain projections, single object, multiple objects, stationary
object, moving object, live objects etc.
[0031] Processor 230 conditions and processes the received reflected RF signal to detect one or
more objects (for example 210) and determines one or more properties of the objects. The
properties of the object thus determined (like shape, size, relative distance, velocity, position in
terms of azimuth and elevation, etc.) are provided to the output device 240. In one embodiment,
the processor 230 performs classification of the object so detected. The processor 230 comprises
signal conditioner to perform signal conditioning operations and provides the conditioned RF
signal for digital processing. The memory 250 may store RF signal like samples of the reflected
RF signal for processing. The processor 230 may temporarily store received data, signal samples,
intermediate data, results of mathematical operations, etc., in the memory 250 (such as buffers,

7

registers etc.,). In an embodiment, the processor 230 may comprise group of signal processing
blocks each performing the specific operations on the received signal and together operative to
detect object and its characteristics/properties. For example, the processor may comprise data
processing blocks / one or more computers coupled through wireless or wire line communication
channels.
[0032] The output device 240 comprises navigation control electronics, display device, decision
making electronic circuitry, traffic management system, vehicular management systems, toll
collection system and other controllers/systems for navigation, display and further processing the
received details of the objects. Accordingly, the system 200 may be deployed as part of unmanned
vehicles, driver assistant systems, for obstacle detection, navigation and control, terrain mapping,
traffic control, toll control etc.
[0033] The RF transceiver 220, processor 230, and memory 250 are implemented as an Integrated
Circuit coupled with computing machines. In that, certain operations of signal processing may be
performed within the integrated circuit and object classification may be performed on the
computing machines or the object classification may also be performed within the IC. The manner
in which the transceiver 220 and the processor 230 (together referred to as Radar object classifier)
may be implemented in an embodiment is further described below.
[0034] FIG. 3 is an example radar transceiver for object detection and recognition in an
embodiment. The radar transceiver 300 is shown comprising transmitting antenna array 310,
transmitter block 315, Local Oscillator (LO) 318, receiving antenna array 320, mixer 325, filter
330 Analog to digital convertor (ADC) 340, Range Detector 350, Doppler Detector 360, Angle of
Arrival (AoA) Detector 370, signal to noise ratio (SNR) estimator 375, Feature Extraction Block
380 and Object Classifier 390. Each element is described in further detail below.
[0035] The transmitting antenna array 310 and the transmitter 315 operate in conjunction to
transmit RF signal over a desired direction. The transmitter 315 generates a radar signal for
transmission and provides the same to the transmitting antenna array 310 for transmission. The
transmitting antenna array 310 is employed to form a transmit beam with an antenna aperture to
illuminate objects at suitable distance and of suitable size. Various known beam forming
techniques may be employed for changing the illuminated region. The transmitter 315 may
generate a radar signal comprising sequence of pulses (as in pulsed radar system) and/or sequence
of chirps (as in Frequency Modulated Continuous Wave (FMCW) radar system).

8

[0036] The receiving antenna array 320 comprises antenna elements, each element capable of
receiving reflected RF signal. The receiving antenna array 320 is employed to form an aperture to
detect objects with a desired resolution (for example object of suitable size). The RF signal
received on each element corresponding to one transmitted RF signal (either pulses or chirps) is
provided to the mixer 325.
[0037] The Mixer 325 mixes RF signal received on each antenna element in the array with the
transmitted RF signal (local oscillator frequency) to generate an intermediate frequency signal (IF
signal). In that the mixer 325 may comprise number of complex or real mixers to mix each RF
signal received on the corresponding antenna elements. Alternatively, the mixer 325 may
comprise of fewer mixers multiplexed to perform desired operation. The number of intermediate
frequency (IF) signal is provided on path 323 to filter 330. The filter 330 passes the IF signal
attenuating the other frequency components (such as various harmonics) received from the mixer.
[0038] The filter 330 may be implemented as a pass band filter to pass a desired bandwidth (in
conjunction with chirp bandwidth BW). The filtered IF signal is provided on path 334 to ADC
340.
[0039] The ADC 340 converts IF signal received on path 334 (analog IF signal) to digital values.
The ADC 340 may sample the analog IF signal at a sampling frequency Fs and convert each
sample value to a bit sequence or binary value. The digitized samples of IF signal (digital IF
signal) is provided for further processing.
[0040] The Range Detector (FFT) 350 detects the range from the received signal. For example,
the range detector 350 may perform FFT on the digital IF samples to generate plurality of ranges
of the plurality of reflected signals (from objects 210). In particular, range FFT 350 performs FFT
on digital IF signal corresponding to each chirp. The Range FFT 350 produces peaks representing
the ranges of the plurality of reflecting points on the objects.
[0041] The Doppler Detector 360 detects the Doppler (or velocity) of each ranges (points on one
or more objects) detected in block 350. For example, the Doppler detector 360 may perform FFT
operation on the ranges across chirps. The peaks in the Doppler FFT represent the Doppler of the
plurality of reflecting points (of objects) or the velocity of the objects. The ranges and Doppler
corresponding to plurality of reflecting points on the objects are provided to the AoA detector
370.

9

[0042] The AoA detector 370 detects position of each reflecting point on the objects and presents
a set of points in azimuth or elevation or both. For example, the AoA detector determines the
angle of arrival of reflected signal (position/location) and estimates the azimuth and/or elevation
of the reflected signal (from the objects) as points to form the point cloud. The range, Doppler,
angles and the SNR, together referred to as primary radar data (Primary Features) is provided to
the feature extraction block 380. FIG. 4A illustrates example point cloud in one embodiment. In
that, each point 410A-410N represents point cloud representing the reflecting points of the objects
reflecting the transmitted RF signal. For example, one vehicle (example of an object) may reflect
RF signal from its multiple points with each point of reflection forming the point in the point
cloud 410A-410N. Each point 410A-410N includes the information of its range, velocity angles
and SNR. FIG. 4B is a table illustrating primary radar data of 410A-410N. The table illustrates

the range 450A-N, velocity 460A-N, azimuth 470A-N and elevation 480A-N of each point 410A-
410N (SNR is avoided only for succinct representation). While the elements 310-370 are

described in brief for completeness, any known techniques for generating the point clouds 410A-
410N may be employed and all such primary radar data generation system are made part of this

disclosure.
[0043] The feature extraction block 380 extracts additional features of the objects from the
primary radar data. The additional features (additional to range, velocity, angles and SNR) may
comprise the length, width, height, trajectory, heading, Doppler distribution, radar cross section
(RCS) of the object, for example. Both primary and additional features (together referred to as
features) are provided to the object classifier 390.
[0044] The object classifier 390 receives/monitors the features to classify objects into different
predefined classes. For example, the classifier may classify the objects into small sized vehicles
(two wheeler), medium sized vehicle (like car) and large sized vehicles (like trucks) so on and
forth, when in case of detecting the vehicles. Alternatively, the classifier may also classify, small,
medium, and large buildings as well. In one embodiment, the object classifier 390 classifies the
objects without the aid of any external information outside of the data generated by the radar
system 300. In one embodiment, the feature extraction block 380 and the object classifier 390
operate in conjunction on the data received over multiple frames. As is well known in the art, one
frame comprises plurality of pulses/chirps transmitted at predefined time intervals. The reflected

10

signals received over one frame on multiple antennas are processed to determine range, velocity,
and angle of arrival (primary radar data).
[0045] The manner in which the feature extraction block 380 and the object classifier 390 may be
implemented in an embodiment to classify the object without the aid of external information is
further described below.
[0046] FIG. 5A is a block diagram illustrating the manner in which the feature extraction block
380 and the object classifier 390 may be implemented in an embodiment. The block diagram is
shown comprising detection block 510, object tracking block 520, training data 530 and object
classifier 540. In that, the detection block 510 detects point(s) from the reflected signals. The
object tracking block 520 is configured to perform operations of grouping points in the point
cloud to form clusters that are representative of different objects and track the clusters over time
to collect extended features of these tracks over an interval of time. The classifier 540 has a
training phase followed by a classification phase and repeated whenever required. In one
embodiment, the object tracking block 520 receives the detected point cloud along with their
associated primary features (including but not limited to range, Doppler velocity, angles and
SNR) from the Detection block 510.The object tracking block 520 generates clusters from the
received point cloud based on one or more parameters or features and draws an extended feature
set per cluster per time instant in addition to tracking this feature set and the associated cluster
over their lifetime, thus forming tracks. Each track is thus associated with a feature set history.**
[0047] FIG. 5B is a table illustrating example multi-dimensional clusters that are being tracked. In
that, the Track ID 560 is representing the tracks. Each track is associated to example features
570A- 570K. For example, dimension 570A representing the feature “length”, dimension 570B
representing the width, dimension 570C representing the height, dimension 570D representing the
area, dimension 570E representing the radar cross section, and dimension 570F representing the
Signal to Noise Ratio (SNR), for example. The classifier 540 classifies the objects/tracks into one
of the predetermined classes based on the training data 530. In one embodiment, the object
detection block 510 and object tracker 520 generate the training data 530 (online) from the
primary radar data and extended features obtained over multiple frames. The training data 530
operate as reference for classification (what is conventionally referred to as ground truth). Thus,
the radar system independently generates for ground truth to train the classifier in an unsupervised
manner, as against the prior art that need to employ additional sensing modalities like camera,

11

LiDAR, etc along with labelled/annotated ground truth generated offline to train the classifier in a
supervised manner. The Manner in which the training data may be generated in an embodiment is
further described below.
[0048] FIG. 6 is a block diagram illustrating the generation of training data 530 in one
embodiment. In block 610, points are detected and a point list with primary features is generated.
In block 620, the detected points are grouped into clusters and an extended feature list per cluster
is compiled. In block 630, the clusters are tracked over multiple frames and an associated feature
set history per track is created. In block 640, an n-D feature space is collated with each track as
point in the n-D feature space. Multiple of these tracks with each track having multiple instances
over time form a dense n-D spatial distribution. In block 650, another clustering of track points
from a subset of N-D distribution or from the complete n-D distribution is formed. One example
may be a k-mean clustering. In block 660, cluster centroids are marked for the formed clusters.
Further, the marked cluster centroid may be reinforced with a-priori information when available.
In block 670, a subset of samples around the centroid is chosen to form a training data per class.
In that, each cluster is representative of a class, forms training data for that class. In bock 680,
grouping of training data per class is performed and provided as learning examples to the
classifier.
[0049] For example, detected points and their features are obtained from the Detection block 510
of Fig 5A. These points are processed and grouped into clusters and an extended feature list per
cluster is prepared. The Object Tracking unit 520 of Fig. 5A monitors these clusters, associating
them over time and prepares a feature set history per track. The feature set history contains the
evolution of the feature set per track over time. Then, an n-dimensional feature space is prepared
where each track and its occurrences over time are laid out onto this n-dimensional feature space.
A second clustering is now performed on a subset or the entire n-dimensional feature space with
multiple tracks and their multiple occurrences over time considered as individual points in this
space. As an example, k-means clustering could be performed in case the number of classes is
known a-priori, otherwise unsupervised forms of clustering can be used. Cluster centroids are
calculated on the clusters that represent class-specific centroid points. These cluster centroids may
be reinforced with information about the classes, if available. Points around each cluster centroid
are picked up as training examples for the particular class and are provided to the classifier to

12

learn the underlying feature set. This way, the training data/ground truth is generated online by the
classifying setup.
[0050] FIG. 7A-7C illustrates sample radar data received over multiple frames and arranged over
multiple selected dimensions. In that, the FIG. 7A illustrating the data points arranged in the
selected two dimensions of object RCS on X- Axis and object Width on Y axis. Similarly, the
FIG. 7B illustrating the data points arranged in the selected two dimensions of RCS on X- Axis
and Velocity on Y axis and FIG. 7C illustrating the data points arranged in the selected two
dimensions of height on X- Axis and width on Y axis, for example. In one embodiment, the
clusters are formed taking the distribution over RCS and Width as in FIG.7A. Similarly, clusters
may be formed using other dimensions as may be the case.
[0051] FIG. 8 illustrates a manner in which clusters are formed in an embodiment. In that, the
track data points are shown arranged over N dimensions with N equal to 2, for example. The
selected features are object/track RCS and the object/track Width. The data points are shown
segregated into K probable classes with K taking a value equal to 3, for example for classifying
objects on road into two-wheelers, small four-wheelers and big four-wheelers. If the required
classifications for determining the object type is 5 (pedestrian, bicycle, two-wheeler, car, truck,
for example), K is set to 5 and so on. The segregated classes are shown as 810, 820 and 830. In
that, any known clustering technique may be employed. For example, the K-means clustering
that provides K number of clusters from the observations, in this case, number of observations
may be the number of data points 800 collected over multiple desired number of radar data frames
(for example 10,000 frames) and K is the number of clusters. By assigning K=3, the clustering
algorithm will deliver three clusters 810, 820 and 830. In the FIG.8, centroids 840, 850 and 860
represent the centroids (a middle point or highest concentration point) of the distribution in the
clusters 810-830 respectively. The centroid points 840-860 may be obtained by several ways as
finding the mean, finding the n-th percentile point, etc., for example. The data points 870, 880 and
890 representing the selected data points from the clusters 810-830, act as training data 530 to
begin with. The data points 870-890 are sigma level sets of data distribution 810-830. For
example, when, nth sigma level set may be represented as “n-s” as is well known in the art, n may
be set to a value equal to 1, the 1-s level set of data points 870-890 may be obtained.
[0052] In one embodiment, the sigma level sets 870-890 may be obtained from relation:

13

x = µ + nS
1/2
[
cos?
sin?] ? ? ? [0,2p], wherein µ representing the expected vector per cluster or
class (each point in the selected training data points 870, 880 and 890 is a n-D vector over the
track’s n-D feature space, for example for 2-D vector of RCS and width, µ =
1
N
Si=0
N-1vi
, where

each vi
is a training data point and hence a 2-D vector as vi = [
RCSi
Widthi
]), n representing the

desired sigma level set, S representing the covariance matrix of the measured vector over the n-
dimensional space, for example. Two dimensional space (RCS, width) and ? varies from 0 to 2p

to construct ellipsoids around the clusters/class centroid.
[0053] In one embodiment, the S may be represented (for the RCS, width) as:
S = [
var(RCS) cov(RCS, width)
cov(RCS, width) var(width)

], where var(a)=variance of a random number a and

cov(a,b)= cross covariance between two random numbers a and b.
by invoking Weak law of Large numbers, above relation may be further represented as:
S = [
?
(xi-µRCS)
2
N
i=N
i=1 ?

(xi-µRCS)(yi-µwidth)
N

i=N
i=1

?
(xi-µRCS)(yi-µwidth)
N

i=N
i=1 ?

(yi-µwidth)
2
N
i=N
i=1

], in that, in that,x_i's and y_i's represent
the i-th RCS and width values from the training data points and µ_RCS and µ_widthrepresent the
mean/expected RCS and width values for a particular cluster/class.
[0054] In certain embodiment, the data points 870-890 may be further validated or reinforced.
FIG. 9 is a graph illustrating the manner in which the data points 870-890 are reinforced. In the
graph, X axis representing the RCS and Y axis representing it’s corresponding probability density.
As shown there the, curve 910, 920 and 930 represents the Probability Distribution/Density
Function (PDF) of cluster 870, 880, and 890 respectively. The data points 870-890 are selected
when the mean position separation 940 and 950 are greater than a threshold. For example, when
the mean position separation 940 and 950 are greater than or equal to 10dB in RCS, the data
points 870-890 are determined as valid.
[0055] It may be appreciated that the data points 800 may be accumulated over the number of
frames until the data points 870-890 meets the required thresholds. Subsequently, the data points
870-890 are provided to the classifier for classification. The classifier 540 may use the data points
870-890 training data to train itself to learn the underlying feature distribution of each class and

14

be able to generalize the learning to new examples when the classifier starts to actually classify
objects.
[0056] While various examples of the present disclosure have been described above, it should be
understood that they have been presented by way of example, and not limitation. Thus, the
breadth and scope of the present disclosure should not be limited by any of the above described
examples, but should be defined in accordance with the following claims and their equivalents. , Claims:We Claim,

1. A radar system comprising:
a transmitter transmitting a radar signal;
a receiver receiving a reflected signal that is a reflection of the radar signal from a
plurality of objects, in that the receiver is configured to generate a point cloud comprising
plurality of points with each point representing a range, a velocity, an angle and a signal to noise
ratio (SNR) information;
a feature extraction unit configured to generate a plurality of tracks from the point cloud
and generating an extended feature set for each track, in that each track representing an object in
the plurality of objects; and
a classifier classifying the plurality of tracks into a set of classes using a reference data
derived from the range, the velocity, the position information and the extended features.
2. The radar system of claim 1, where in the extended feature set comprising a width
and a radar cross section (RCS) and the set of class comprising two-wheeler, cars and trucks,
wherein plurality of tracks are generated by generating three clusters of points from the point
cloud when arranged over the RCS and width.
3. The radar system of claim 1, where in the feature extension unit is configured to
generate the reference data.
4. The radar system of claim 3, where in the feature extension unit is configured to
select a first set of points from each cluster that are within a first distance from its centroid.
5. The radar system of claim 4, where in the feature extension unit is configured to
select a first set of points from each cluster when the centroids are separated by a threshold.
6. A method of classifying a plurality of detected objects in a radar system
comprising:
receiving a reflected signal that is a reflection of a radar signal from a plurality of objects;
generating a point cloud, from the reflected signal, the point cloud comprising plurality
of points with each point representing a range, a velocity, an angle and a signal to noise ratio
(SNR) information;

16

grouping the plurality of points into clusters and compiling an extended feature list per
cluster;
tracking each cluster and creating an associated feature set history per track;
collating an n-dimensional (n-D) feature space to form an n-D distribution of track points
with each track as point in the space;
performing another clustering on a subset of n-D distribution of track points to generate a
second set of clusters
identifying centroid of each cluster in the second set of cluster;
selecting a subset of samples around the centroid to form a training data per class; and
grouping training data per class and providing as learning examples to the classifier
classifying the cluster into one of the classes.
7. A method, system and apparatus providing one or more features as described in
the paragraphs of this specification.