Claims:We Claim:
1. A system for detecting parking occupancy, comprising:
an enclosure (101);
a sensor system (102) provided in the enclosure (101) for detecting parameters;
a processor complex (103) provided in the enclosure (101) for controlling the sensor system (102);
a battery (104) provided in the enclosure (101) for powering the sensor system (102) and the processor complex (103);
characterized in that
the sensor system (102) detecting parameters of presence of a vehicle, position of vehicle, ambient temperature, ambient light and voltage provided by the battery and transmitting the detected parameters to the processor complex (103);
a cloud server (108) communicating with the processor complex (103) through a communication network (106) for accessing the detected parameters; and
a machine learning module (110) connected to the cloud server (108) for transmitting input to the processor complex (103) based on the detected parameters of the sensor system (102).
2. The system as claimed in claim 1, wherein the processor complex (103) includes a low power microcontroller having an embedded firmware for controlling the sensor system (102).
3. The system as claimed in claim 1, wherein control of the sensor system (102) by the processor complex (103) includes switching on, switching off and calibrating sensors in the sensor system (102).
4. The system as claimed in claim 1, wherein the sensor system (102) includes a magnetometer (201), a time-of-flight sensor (202), a temperature sensor (203), a daylight measurement sensor (204) and a voltage measurement sensor (205).
5. The system as claimed in claim 1, wherein the machine learning module (110) transmits input to the processor complex (103) for calibrating the sensor system (102) to improve accuracy of detection based on detected parameters received from the sensor system (102).
6. The system as claimed in claim 1, wherein a magnetic switch is provided in the processor complex (103) for turning on, turning off and maintaining low power supply from the battery (104).
7. The system as claimed in claim 1, wherein the machine learning module (110) analyses the detected parameters of the sensor system (102) for predicting a future presence of a vehicle in a location.
8. The system as claimed in claim 1, wherein the processor complex (103) communicates with the cloud server (108) through a LoraWAN network.
9. The system as claimed in claim 1, wherein a buck-boost DC-DC converter is provided in the processor complex (103) for ensuring stable power supply from the battery (104).
10. The system as claimed in claim 1, wherein the enclosure (101) includes a base for fixing at a location, a top for housing the sensor system (102) and the processor complex (103) and a cover for enclosing the battery (104).
, Description:FIELD
[0001] The embodiments herein generally relate to detecting occupancy of vehicles in a parking. More particularly, the disclosure relates to a system providing real time detection of vehicle occupancy in a parking.

BACKGROUND AND PRIOR ART
[0002] Increasing number of vehicles necessitates effective parking strategies for managing the vehicles in a limited amount of space in reduced duration of time. Various parking places such as parking lots off street, parking lots in offices and malls, curb side parking lots all require parking management for improving urban mobility. Vehicular parking management saves time, reduces congestion, and enhances consumer experience. Real time parking availability information is essential for both the consumer and the parking operator.
[0003] Generally, parking occupancy sensors are provided for detecting presence of vehicles in a parking space. However, these sensors are static and fail to function effectively over time. Further, the sensors are not adaptable to the changing scenarios of the parking facility. Providing real time and future parking availability information enables parking management in resource planning, future prediction, dynamic pricing, among others. Also, providing prior parking availability information to a consumer enables the consumer to make commute choices, reduce carbon footprint, enhance consumer experience and saves time.
[0004] Therefore, there is a need for an improved and effective system for parking management. Moreover, there is a need for an adaptable system to detect real time occupancy of vehicles in a parking.
OBJECTS
[0005] Some of the objects of the present disclosure are described herein below:
[0006] The main objective of the present disclosure is to provide a system for detecting occupancy of vehicles in a parking.
[0007] Another objective of the present disclosure is to provide a system for predicting future needs of parking management.
[0008] Still another objective of the present disclosure is to provide a system for providing real time parking occupancy data.
[0009] Yet another objective of the present disclosure is to provide a wireless and adaptable system for detecting occupancy of vehicles in a parking.
[00010] The other objectives and advantages of the present disclosure will be apparent from the following description when read in conjunction with the accompanying drawings, which are incorporated for illustration of preferred embodiments of the present disclosure and are not intended to limit the scope thereof.

SUMMARY
[00011] In view of the foregoing, an embodiment herein provides a system for detecting parking occupancy.
[00012] In accordance with an embodiment, the system includes an enclosure, a sensor system provided in the enclosure for detecting parameters, a processor complex provided in the enclosure for controlling the sensor system and a battery provided in the enclosure for powering the sensor system and the processor complex. The sensor system detects parameters of presence of a vehicle, position of vehicle, ambient temperature, ambient light and voltage provided by the battery and transmits the detected parameters to the processor complex. A cloud server communicates with the processor complex through a communication network for accessing the detected parameters and a machine learning module is connected to the cloud server for transmitting input to the processor complex based on the detected parameters of the sensor system. In an embodiment, the sensor system includes a magnetometer, a time-of-flight sensor, a temperature sensor, a daylight measurement sensor and a voltage measurement sensor.
[00013] In accordance with an embodiment, the processor complex includes a low power microcontroller having an embedded firmware for controlling the sensor system. In an embodiment, control of the sensor system by the processor complex includes switching on, switching off and calibrating sensors in the sensor system. In an embodiment, a magnetic switch is provided in the processor complex for turning on, turning off and maintaining low power supply from the battery.
[00014] In accordance with an embodiment, the processor complex communicates with the cloud server through a LoraWAN network. In an embodiment, the machine learning module analyses the detected parameters of the sensor system for predicting a future presence of a vehicle in a location. In an embodiment, the machine learning module transmits input to the processor complex for calibrating the sensor system to improve accuracy of detection based on detected parameters received from the sensor system.
[00015] In accordance with an embodiment, a buck-boost DC-DC converter is provided in the processor complex for ensuring stable power supply from the battery.
[00016] In accordance with an embodiment, the enclosure includes a base for fixing at a location, a top for housing the sensor system and the processor complex and a cover for enclosing the battery.
[00017] These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.

BRIEF DESCRIPTION OF DRAWINGS
[00018] The detailed description is set forth with reference to the accompanying figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The use of the same reference numbers in different figures indicates similar or identical items.
[00019] Fig.1 illustrates a block diagram of a system for detecting parking occupancy, according to an embodiment herein;
[00020] Fig.2 illustrates a block diagram of the enclosure of the apparatus, according to an embodiment herein;
[00021] Fig.3a illustrates a perspective view of the enclosure, according to an embodiment herein;
[00022] Fig. 3b illustrates a perspective view of the base of the enclosure, according to an embodiment herein;
[00023] Fig. 3c illustrates a perspective view of the top of the enclosure, according to an embodiment herein; and
[00024] Fig. 3d illustrates a perspective view of the cover of the enclosure, according to an embodiment herein.

LIST OF NUMERALS
101 - Enclosure
102 - Sensor system
103 - Processor complex
104 - Battery
106 - Communication network
108 - Cloud server
110 - Machine learning module
201 - Magnetometer
202 - Time of flight sensor
203 - Temperature sensor
204 - Day light measurement sensor
205 - Voltage measurement sensor
300 - Perspective views of enclosure and components of the enclosure

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[00025] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments and detailed in the following description. Descriptions of well-known components and processing techniques are omitted soas to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
[00026] As mentioned above, there is a need there is a need for an improved and effective system for parking management. In particular, there is a need for an adaptable system for detecting real time occupancy of vehicles in a parking. The embodiments herein achieve this by providing “A system for detecting parking occupancy”. Referring now to the drawings, and more particularly to Fig.1 through Fig.3d, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments.
[00027] Fig.1 illustrates a block diagram of a system for detecting parling occupancy. The system 100 includes an enclosure 101, a communication network 106, a cloud server 108 and a machine learning module 110.
[00028] In an embodiment, the enclosure 101 includes a sensor system 102, a processor complex103 and a battery 104. The enclosure 101 is provided for housing the sensor system 102, the processor complex 103 and the battery 104. The enclosure is fixed at parking spaces for enabling detection of occupancy of vehicles as per user requirement. The enclosure is machine tooled. A material of the enclosure is plastic, preferably Polycarbonate - Acrylonitrile Butadiene Styrene (PC - ABS). The enclosure 101 is resistant to direct sunlight, dust, water logging and weight of four-wheeled vehicles, thereby protecting the sensor system 102, the processor complex 103 and the battery 104.
[00029] In an embodiment, the sensor system 102 is provided for detecting parameters in the location of the parking. The parameters include but not limited to presence of vehicle in a location, position of vehicle in a location, ambient light, ambient temperature and voltage present in the system.
[00030] In an embodiment, the processor complex 103 is connected to the sensor system 102. The detected parameters from the sensor system 102 are transmitted to the processor complex 103. The processor complex 103 includes a microcontroller provided for controlling the sensor system 102. The microcontroller is a low power microcontroller including embedded firmware for long duration functioning.
[00031] In an embodiment, the processor complex 103 communicates to the sensor system 102 using but not limited to SPI, I2C and GPIO. The microcontroller 103 controls the sensor system 102 including turning ON and turning OFF using the firmware through SPI and I2C. The processor complex 103 powers the sensor system 102 using DC power from a battery 104 and manages power utilization. The firmware processor complex 103 turns off power to the sensor system 102 allowing for a very low power sleep, thereby enhancing battery life. The processor complex 103 includes access to a non-volatile storage for maintaining configuration parameters of the sensor system 102 intact and the embedded firmware of the microcontroller acts on a remote reboot command for restarting the sensor system 102 on detecting any non-recoverable error. A hardware watchdog in the microcontroller protects logic of the firmware for ensuring the system does not hang or stop responding.
[00032] In an embodiment, the processor complex 103, the sensor system 102 and the battery 104 are provided in a Printed Circuit Board (PCB) of dual layer configuration with military grade formal coating to withstand environmental damage from heat, moisture and dust.
[00033] In an embodiment, the battery 104 is provided for powering the sensor system 102 and the microcontroller 103. In an embodiment, the battery is Lithium Thionyl Chloride battery (Li-SOCl2). The battery causes a voltage dip due to high impedance of LiSOCl2. A buck and boost DC-DC converter is provided in the processor complex (103) for ensuring stable power supply from the Lithiun Thionyl Chloride battery. In an embodiment, operating voltage is 3.6v 8000mAH and operating current is in a range of 5mA – 120mA.
[00034] In an embodiment, the cloud server 108 is provided for communicating with the processor complex 103 through a communication network 106. The processor complex 103 transmits values of parameters detected by the sensor system 102 to the cloud server 108. The cloud server 108 includes a database for storing the values of the parameters corresponding to their time, data and location.
[00035] In an embodiment, the cloud server 108 is connected to the machine learning module 110. The machine learning module 110 uses the stored values of parameters detected by the sensor system 102 for predicting a future occupancy of vehicles in a parking location. The machine learning module 110 transmits inputs for the sensor system 102 through the cloud server 108 to the processor complex 103. The firmware of the microcontroller in the processor complex 103 controls the sensor system 102 based on the input from the machine learning module 110. The machine learning module 110 provides input to the processor complex 103 for turning off abnormal or non-functional sensor system 103. The machine learning module 110 transmits input to the microcontroller of the processor complex 103 for turning off sensors of the sensor system 102 when detecting the sensor system 102 not actively working thereby allowing very low sleep current. In an embodiment, duration of sleep of the sensor system 102 is between 10 seconds and 50 seconds and sleep current drawn is less than 2µA.
[00036] The machine learning module 110 provides predicted future needs of parking infrastructure, usage graph of occupancy of vehicles in a parking lot and resources needed for managing the parking lot. A parking operator can use the data from the system for adding pre-booking, “park and pay” options in mobile application. The prediction of the machine learning module 110 becomes more accurate a usage of the system increases.
[00037] Fig.2 illustrates a block diagram of the enclosure of the apparatus. The sensor system 102 comprises a plurality of sensors including but not limited to a magnetometer 201, a time-of-flight sensor 202, a temperature sensor 203, a day light measurement sensor 204, and a voltage measurement sensor 205.
[00038] The magnetometer 201 is provided for detecting presence of a vehicle in a parking. The time-of-flight sensor 202 is provided for detecting presence and position of vehicle in a parking. In an embodiment, the time-of-flight sensor is an infrared time-of-flight sensor. The temperature sensor 203 is provided for measuring ambient temperature of location of vehicle in a parking. The day light measurement sensor 204 is provided for measuring amount of light in the location of vehicle in a parking. The voltage measurement sensor 205 is provided for measuring voltage in the enclosure 101.
[00039] In an embodiment, detected and measured parameters from the plurality of sensors are transmitted to the microcontroller in the processor complex 103. The processor complex 103 transmits values of the detected and measured parameters to the cloud server 108 through the communication network 106. The machine learning module 110 analyses the values of the detected and measured parameters. Based on the analysis, the machine learning module 110 transmits input to the processor complex through the cloud server 108 for turning on, turning off, or calibrating specific sensors in the sensor system 102. The firmware of the microcontroller in the processor complex 103 controls the sensor system 102 based on the received input from the machine learning module 110.
[00040] In an embodiment, on detecting absence of vehicles by the magnetometer 201 and the time-of-flight sensor 202 for a longer duration of time, the machine learning module 110 transmits input to the processor complex 103 through the cloud server 108 for supplying low power to the sensor system 102. In an embodiment, the user device includes but not limited to mobile phone, smart phone, laptop.
[00041] In an embodiment, the temperature sensor 203 senses temperature. On detecting magnetic flux variance of the magnetometer 201, the machine learning module 110 receives and analyses temperature data from the temperature sensor 203 for compensating. The machine learning module 110 then recalibrates the magnetometer 201 through the processor complex 103 for accurate detection of vehicles. In an embodiment, the daylight measurement 204 sensor senses light at a parking location. On detecting direct daylight at the parking location, the cloud server 108 is backed to compensate for the light as reading of the time-of-flight sensor 202 is susceptible to error in direct daylight. The reading from the time-of-flight sensor is transmitted to the machine learning module 110, wherein based on the reading the machine learning module 110 commands the microcontroller in the processor complex 103 for calibration of the parameters of the time-of-flight sensor 202. In an embodiment, on detecting voltage by the voltage measurement sensor 205, the machine learning module 110 correspondingly transmits input through the cloud server 108 to the processor complex 103 for controlling the boost DC-DC converter.
[00042] In an embodiment, the temperature sensor 203 is provided for detecting ambient temperature and transmitting the temperature through the cloud server 108 to a user device of a parking operator for managing resources of air conditioning, heater, fans. In an embodiment, the day light measurement sensor 204 is provided for detecting ambient day light and transmitting the daylight data through the cloud server 108 to a user device of a parking operator for switching on/ switching off lights in the parking.
[00043] In an embodiment, a RF (radio frequency) module is connected to the processor complex 103 over SPI. The RF module is provided for communication of the processor complex 103 through the communication network 106. The RF module is a slave to the firmware in the microcontroller of the processor complex 103. In an embodiment, the communication network 106 is LoraWAN network. In an embodiment, range of communication of the LoraWAN network is between 300 meters and 1500 meters. The RF module transmits telemetry data including detected parameters of the sensor system 102 to a Lora Base station in the LoraWAN network. In an embodiment, the RF module integrates a 5dB gain antenna on the PCB. RF shielding is provided for the RF module to minimize frequency distortion. The RF module supports enhanced security for payloads using AES encryption and node identification and activation methods.
[00044] In an embodiment, the RF module implements Lora specification. In a preferred embodiment, the RF module uses Semtech’s ASIC supporting frequency range from 300Mhz to 1Ghz. In an embodiment, the firmware on the processor complex 103 and the LoraWAN network control frequency bands in use.
[00045] In an embodiment, telemetry data including detected parameters of the sensor system 102 are transmitted to the cloud server 108 through the communication network.
[00046] The cloud server 108 transmits input from the machine learning module 110 to the RF module through the LoraWAN network.
[00047] In an embodiment, a wired internet up link connected to the LoRa base station and a cellular end point are provided in the LoraWAN network for facilitating communication to a plurality of IoT (Internet of things) devices and serve data over large location wirelessly.
[00048] In an embodiment, the communication network 106 is a conventional network and not limited to LoraWAN network for facilitating communication between the processor complex 103, the cloud server 108 and IoT (Internet of Things) devices.
[00049] Fig.3a illustrates a perspective view of the enclosure. The enclosure is provided for housing and protecting the sensor system 102, the processor complex 103 and the battery 104. The enclosure 101 includes three discrete components. The components include a base, a top and a cover. The enclosure 101 facilitates ease of fixing, ease of servicing and durability. In an embodiment, degree of protection offered by the enclosure 101 is IP67.
[00050] Fig. 3b illustrates a perspective view of the base of the enclosure. The base is provided for fixing at a location in a parking space using fasteners not limited to screws, nails. The base ensures electronics is not damaged while fixing of the sensor system 102.
[00051] Fig. 3c illustrates a perspective view of the top of the enclosure 101. The top is provided for housing the sensor system 102 and the processor complex 103.
[00052] Fig. 3d illustrates a perspective view of the cover of the enclosure. The cover is provided for enclosing the battery 104. The top and the cover are fixed and sealed with silicone gel and plugged onto the base. The top assembly is field replaceable using a locking mechanism from the base. In an embodiment, weight of the enclosure including the sensor system, the processor complex and the battery is less than 500 grams. In an embodiment, the system 100 is capable of working in a temperature range between -20° Celsius and 80° Celsius. In an embodiment, service life of the system 100 is up to 5 years.
[00053] A main advantage of the present disclosure is that the system provides real time data of occupancy of vehicles in a parking.
[00054] Another advantage of the present disclosure is that the system predicts future needs of parking occupancy for parking management.
[00055] Still another advantage of the present disclosure is that the system is auto configurable based on machine learning for providing real time and future occupancy of vehicles in a parking.
[00056] Yet another advantage of the present disclosure is that the system provides an adaptable and wireless system which minimizes human intervention for providing real time and future parking occupancy data.
[00057] Another advantage of the present disclosure is that the system facilitates dynamic pricing for parking based on the predicted data, resource optimization in a parking, citizen service, city planning and helps to reduces carbon footprint.
[00058] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodimentsherein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.