Efficient Deep Learning Models for Privacy-preserving People Counting on Low-resolution Infrared Arrays

• URL: http://arxiv.org/abs/2304.06059v2
• Date: Tue, 5 Dec 2023 09:16:40 GMT
• Title: Efficient Deep Learning Models for Privacy-preserving People Counting on Low-resolution Infrared Arrays
• Authors: Chen Xie, Francesco Daghero, Yukai Chen, Marco Castellano, Luca Gandolfi, Andrea Calimera, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari
• Abstract summary: Infrared (IR) array sensors offer a low-cost, energy-efficient, and privacy-preserving solution for people counting. Previous work has shown that Deep Learning (DL) can yield superior performance on this task. We compare 6 different DL architectures on a novel dataset composed of IR images collected from a commercial 8x8 array.
• Score: 11.363207467478134
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Ultra-low-resolution Infrared (IR) array sensors offer a low-cost, energy-efficient, and privacy-preserving solution for people counting, with applications such as occupancy monitoring. Previous work has shown that Deep Learning (DL) can yield superior performance on this task. However, the literature was missing an extensive comparative analysis of various efficient DL architectures for IR array-based people counting, that considers not only their accuracy, but also the cost of deploying them on memory- and energy-constrained Internet of Things (IoT) edge nodes. In this work, we address this need by comparing 6 different DL architectures on a novel dataset composed of IR images collected from a commercial 8x8 array, which we made openly available. With a wide architectural exploration of each model type, we obtain a rich set of Pareto-optimal solutions, spanning cross-validated balanced accuracy scores in the 55.70-82.70% range. When deployed on a commercial Microcontroller (MCU) by STMicroelectronics, the STM32L4A6ZG, these models occupy 0.41-9.28kB of memory, and require 1.10-7.74ms per inference, while consuming 17.18-120.43 $\mu$J of energy. Our models are significantly more accurate than a previous deterministic method (up to +39.9%), while being up to 3.53x faster and more energy efficient. Further, our models' accuracy is comparable to state-of-the-art DL solutions on similar resolution sensors, despite a much lower complexity. All our models enable continuous, real-time inference on a MCU-based IoT node, with years of autonomous operation without battery recharging.

Related papers

• Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers [56.37495946212932]
  Vision transformers (ViTs) have demonstrated their superior accuracy for computer vision tasks compared to convolutional neural networks (CNNs) This work proposes Quasar-ViT, a hardware-oriented quantization-aware architecture search framework for ViTs.
  arXiv  Detail & Related papers  (2024-07-25T16:35:46Z)
• A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism [58.855741970337675]
  Neural architecture search (NAS) enables re-searchers to automatically explore vast search spaces and find efficient neural networks. NAS suffers from a key bottleneck, i.e., numerous architectures need to be evaluated during the search process. We propose the SMEM-NAS, a pairwise com-parison relation-assisted multi-objective evolutionary algorithm based on a multi-population mechanism.
  arXiv  Detail & Related papers  (2024-07-22T12:46:22Z)
• HW-SW Optimization of DNNs for Privacy-preserving People Counting on Low-resolution Infrared Arrays [9.806742394395322]
  Low-resolution infrared (IR) array sensors enable people counting applications such as monitoring the occupancy of spaces and people flows. Deep Neural Networks (DNNs) have been shown to be well-suited to process these sensor data in an accurate and efficient manner. We propose a highly automated full-stack optimization flow for DNNs that goes from neural architecture search, mixed-precision quantization, and post-processing.
  arXiv  Detail & Related papers  (2024-02-02T08:45:38Z)
• Dynamic Decision Tree Ensembles for Energy-Efficient Inference on IoT Edge Nodes [12.99136544903102]
  Decision tree ensembles, such as Random Forests (RFs) and Gradient Boosting (GBTs) are particularly suited for this task, given their relatively low complexity. This paper proposes the use of dynamic ensembles, that adjust the number of executed trees based both on a latency/energy target and on the complexity of the processed input. We focus on deploying these algorithms on multi-core low-power IoT devices, designing a tool that automatically converts a Python ensemble into optimized C code.
  arXiv  Detail & Related papers  (2023-06-16T11:59:18Z)
• Multi-Complexity-Loss DNAS for Energy-Efficient and Memory-Constrained Deep Neural Networks [22.40937602825472]
  Energy and memory are rarely considered simultaneously, in particular by low-search-cost Differentiable (DNAS) solutions. We propose the first DNAS that directly addresses the most realistic scenario from a designer's perspective. Our networks span a range of 2.18x in energy consumption and 4.04% in accuracy for the same memory constraint, and reduce energy by up to 2.2x with negligible accuracy drop with respect to the baseline.
  arXiv  Detail & Related papers  (2022-06-01T08:04:50Z)
• Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection [58.81316192862618]
  Two critical sensors for 3D perception in autonomous driving are the camera and the LiDAR. fusing these two modalities can significantly boost the performance of 3D perception models. We benchmark the state-of-the-art fusion methods for the first time.
  arXiv  Detail & Related papers  (2022-05-30T09:35:37Z)
• Privacy-preserving Social Distance Monitoring on Microcontrollers with Low-Resolution Infrared Sensors and CNNs [10.80166668204102]
  Low-resolution infrared (IR) array sensors offer a low-cost, low-power, and privacy-preserving alternative to optical cameras and smartphones/wearables. We demonstrate that an accurate detection of social distance violations can be achieved processing the raw output of a 8x8 IR array sensor with a small-sized Convolutional Neural Network (CNN) We show that our best CNN achieves 86.3% balanced accuracy, significantly outperforming the 61% achieved by a state-of-the-art deterministic algorithm.
  arXiv  Detail & Related papers  (2022-04-22T07:17:45Z)
• Deep Learning for Real Time Satellite Pose Estimation on Low Power Edge TPU [58.720142291102135]
  In this paper we propose a pose estimation software exploiting neural network architectures. We show how low power machine learning accelerators could enable Artificial Intelligence exploitation in space.
  arXiv  Detail & Related papers  (2022-04-07T08:53:18Z)
• ANNETTE: Accurate Neural Network Execution Time Estimation with Stacked Models [56.21470608621633]
  We propose a time estimation framework to decouple the architectural search from the target hardware. The proposed methodology extracts a set of models from micro- kernel and multi-layer benchmarks and generates a stacked model for mapping and network execution time estimation. We compare estimation accuracy and fidelity of the generated mixed models, statistical models with the roofline model, and a refined roofline model for evaluation.
  arXiv  Detail & Related papers  (2021-05-07T11:39:05Z)
• FRDet: Balanced and Lightweight Object Detector based on Fire-Residual Modules for Embedded Processor of Autonomous Driving [0.0]
  We propose a lightweight one-stage object detector that is balanced to satisfy all the constraints of accuracy, model size, and real-time processing. Our network aims to maximize the compression of the model while achieving or surpassing YOLOv3 level of accuracy.
  arXiv  Detail & Related papers  (2020-11-16T16:15:43Z)
• DDPNAS: Efficient Neural Architecture Search via Dynamic Distribution Pruning [135.27931587381596]
  We propose an efficient and unified NAS framework termed DDPNAS via dynamic distribution pruning. In particular, we first sample architectures from a joint categorical distribution. Then the search space is dynamically pruned and its distribution is updated every few epochs. With the proposed efficient network generation method, we directly obtain the optimal neural architectures on given constraints.
  arXiv  Detail & Related papers  (2019-05-28T06:35:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.