Efficient People Counting in Thermal Images: The Benchmark of Resource-Constrained Hardware
The monitoring of presence is a timely topic in intelligent building management systems. Nowadays, most rooms, halls, and auditoriums use a simple binary presence detector that is used to control the operation of HVAC systems. This strategy is not optimal and leads to significant amounts of energy b...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9964383/ |
| _version_ | 1811205191187300352 |
|---|---|
| author | Mateusz Piechocki Marek Kraft Tomasz Pajchrowski Przemyslaw Aszkowski Dominik Pieczynski |
| author_facet | Mateusz Piechocki Marek Kraft Tomasz Pajchrowski Przemyslaw Aszkowski Dominik Pieczynski |
| author_sort | Mateusz Piechocki |
| collection | DOAJ |
| description | The monitoring of presence is a timely topic in intelligent building management systems. Nowadays, most rooms, halls, and auditoriums use a simple binary presence detector that is used to control the operation of HVAC systems. This strategy is not optimal and leads to significant amounts of energy being wasted due to inadequate control of the system. Therefore, knowing the exact person count facilitates better adjustment to current needs and cost reduction. The vision-based people-counting is a well-known area of computer vision research. In addition, with rapid development in the artificial intelligence and IoT sectors, power-limited and resource-constrained devices like single-board computers or microcontrollers are able to run even such sophisticated algorithms as neural networks. This capability not only ensures the tiny size and power effectiveness of the device but also, by definition, preserves privacy by limiting or completely eliminating the transfer of data to the cloud. In this paper, we describe the method for efficient occupancy estimation based on low-resolution thermal images. This approach uses a U-Net-like convolutional neural network that is capable of estimating the number of people in the sensor’s field of view. Although the architecture was optimized and quantized to fit the limited microcontroller’s memory, the metrics obtained by the algorithm outperform the other state-of-the-art solutions. Additionally, the algorithm was deployed on a range of embedded devices to perform a set of benchmarks. The tests carried out on embedded processors allowed the comparison of a wide range of chips and proved that people counting can be efficiently executed on resource-limited hardware while maintaining low power consumption. |
| first_indexed | 2024-04-12T03:26:34Z |
| format | Article |
| id | doaj.art-d8cbc8e8f7b743fd9e7b7e9af2e08b36 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T03:26:34Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d8cbc8e8f7b743fd9e7b7e9af2e08b362022-12-22T03:49:41ZengIEEEIEEE Access2169-35362022-01-011012483512484710.1109/ACCESS.2022.32252339964383Efficient People Counting in Thermal Images: The Benchmark of Resource-Constrained HardwareMateusz Piechocki0https://orcid.org/0000-0002-3479-0237Marek Kraft1https://orcid.org/0000-0001-6483-2357Tomasz Pajchrowski2https://orcid.org/0000-0002-0002-7161Przemyslaw Aszkowski3Dominik Pieczynski4Institute of Robotics and Machine Intelligence, Poznan University of Technology, Poznan, PolandInstitute of Robotics and Machine Intelligence, Poznan University of Technology, Poznan, PolandInstitute of Robotics and Machine Intelligence, Poznan University of Technology, Poznan, PolandInstitute of Robotics and Machine Intelligence, Poznan University of Technology, Poznan, PolandInstitute of Robotics and Machine Intelligence, Poznan University of Technology, Poznan, PolandThe monitoring of presence is a timely topic in intelligent building management systems. Nowadays, most rooms, halls, and auditoriums use a simple binary presence detector that is used to control the operation of HVAC systems. This strategy is not optimal and leads to significant amounts of energy being wasted due to inadequate control of the system. Therefore, knowing the exact person count facilitates better adjustment to current needs and cost reduction. The vision-based people-counting is a well-known area of computer vision research. In addition, with rapid development in the artificial intelligence and IoT sectors, power-limited and resource-constrained devices like single-board computers or microcontrollers are able to run even such sophisticated algorithms as neural networks. This capability not only ensures the tiny size and power effectiveness of the device but also, by definition, preserves privacy by limiting or completely eliminating the transfer of data to the cloud. In this paper, we describe the method for efficient occupancy estimation based on low-resolution thermal images. This approach uses a U-Net-like convolutional neural network that is capable of estimating the number of people in the sensor’s field of view. Although the architecture was optimized and quantized to fit the limited microcontroller’s memory, the metrics obtained by the algorithm outperform the other state-of-the-art solutions. Additionally, the algorithm was deployed on a range of embedded devices to perform a set of benchmarks. The tests carried out on embedded processors allowed the comparison of a wide range of chips and proved that people counting can be efficiently executed on resource-limited hardware while maintaining low power consumption.https://ieeexplore.ieee.org/document/9964383/Benchmark testingdeep learningedge computingneural networksthermal imagingmicrocontrollers |
| spellingShingle | Mateusz Piechocki Marek Kraft Tomasz Pajchrowski Przemyslaw Aszkowski Dominik Pieczynski Efficient People Counting in Thermal Images: The Benchmark of Resource-Constrained Hardware IEEE Access Benchmark testing deep learning edge computing neural networks thermal imaging microcontrollers |
| title | Efficient People Counting in Thermal Images: The Benchmark of Resource-Constrained Hardware |
| title_full | Efficient People Counting in Thermal Images: The Benchmark of Resource-Constrained Hardware |
| title_fullStr | Efficient People Counting in Thermal Images: The Benchmark of Resource-Constrained Hardware |
| title_full_unstemmed | Efficient People Counting in Thermal Images: The Benchmark of Resource-Constrained Hardware |
| title_short | Efficient People Counting in Thermal Images: The Benchmark of Resource-Constrained Hardware |
| title_sort | efficient people counting in thermal images the benchmark of resource constrained hardware |
| topic | Benchmark testing deep learning edge computing neural networks thermal imaging microcontrollers |
| url | https://ieeexplore.ieee.org/document/9964383/ |
| work_keys_str_mv | AT mateuszpiechocki efficientpeoplecountinginthermalimagesthebenchmarkofresourceconstrainedhardware AT marekkraft efficientpeoplecountinginthermalimagesthebenchmarkofresourceconstrainedhardware AT tomaszpajchrowski efficientpeoplecountinginthermalimagesthebenchmarkofresourceconstrainedhardware AT przemyslawaszkowski efficientpeoplecountinginthermalimagesthebenchmarkofresourceconstrainedhardware AT dominikpieczynski efficientpeoplecountinginthermalimagesthebenchmarkofresourceconstrainedhardware |