mlsanityData to 7 Oct 2026

Person Detection Using an Ultra Low-resolution Thermal Imager on a Low-cost MCU

arXiv 2212.08415 ↗First posted 16 Dec 2022cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Detecting persons in images or video with neural networks is a well-studied subject in literature. However, such works usually assume the availability of a camera of decent resolution and a high-performance processor or GPU to run the detection algorithm, which significantly increases the cost of a complete detection system. However, many applications require low-cost solutions, composed of cheap sensors and simple microcontrollers. In this paper, we demonstrate that even on such hardware we are not condemned to simple classic image processing techniques. We propose a novel ultra-lightweight CNN-based person detector that processes thermal video from a low-cost 32x24 pixel static imager. Trained and compressed on our own recorded dataset, our model achieves up to 91.62% accuracy (F1-score), has less than 10k parameters, and runs as fast as 87ms and 46ms on low-cost microcontrollers STM32F407 and STM32F746, respectively.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 38 references that are in the map. First posted on arXiv 16 Dec 2022.

Builds on

24 of 38 references.

References · 24

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2017Mask R-CNNcited by 7,259
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  6. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  7. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  8. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  9. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  10. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  11. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  12. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
12 more
  1. 2021A White Paper on Neural Network Quantizationcited by 453
  2. 2018Soft Filter Pruning for Accelerating Deep Convolutional Neural Networkscited by 313
  3. 2020MCUNet: Tiny Deep Learning on IoT Devicescited by 269
  4. 2018CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUscited by 116
  5. 2016T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videoscited by 67
  6. 2018Task-Driven Super Resolution: Object Detection in Low-resolution Imagescited by 52
  7. 2017Mobile Video Object Detection with Temporally-Aware Feature Mapscited by 39
  8. 2019YOLO Nano: a Highly Compact You Only Look Once Convolutional Neural Network for Object Detectioncited by 16
  9. 2020Anchor-free Small-scale Multispectral Pedestrian Detectioncited by 8
  10. 2020Revisiting Loss Modelling for Unstructured Pruningcited by 6
  11. 20183D-DETNet: a Single Stage Video-Based Vehicle Detectorcited by 3
  12. 2020How low can you go? Privacy-preserving people detection with an omni-directional cameracited by 2

Built on by

Not cited yet.