Real-time multiple people gait recognition in the edge
Open Access
- 2 June 2025
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-11
Abstract
Deploying deep learning models on edge devices offers advantages in terms of data security and communication latency. However, optimizing these models to achieve fast computing speeds without sacrificing accuracy can be challenging, especially in video surveillance applications where real-time processing is crucial. In this study, we investigate the deployment of gait recognition models as a multi-objective selection problem in which we seek to simultaneously minimize several objectives, such as latency and energy consumption, while maintaining accuracy. The decision space of a problem comprises all models that can be built by varying parameters, such as the size of the model, the operating frequency of the device, and the precision of the operations. From this problem definition, a subset of Pareto optimal models can be selected to be deployed on the target device. We conducted experiments with two different gait recognition models on NVIDIA Jetson Orin Nano and Jetson AGX Orin to explore their decision spaces. In addition, we investigated different strategies to increase the throughput of the deployed models by taking advantage of batching and concurrent execution. Together, these techniques allowed us to design real-time solutions for gait recognition in scenarios with multiple subjects. These solutions can process between 42 and 188 simultaneous subjects at 25 inferences per second with an energy consumption ranging from 6.31 to 9.71 mJ per inference, depending on the device and the deployed model.Keywords
Funding Information
- Ministerio de Educación de España (PID2022-136575OB-I00)
This publication has 39 references indexed in Scilit:
- Intelligent obstacle avoidance algorithm for safe urban monitoring with autonomous mobile dronesJournal of Electronic Science and Technology, 2024
- Increased Leverage of Transprecision Computing for Machine Vision Applications at the EdgeJournal of Signal Processing Systems, 2022
- Pruning and quantization for deep neural network acceleration: A surveyNeurocomputing, 2021
- AutoPruner: An end-to-end trainable filter pruning method for efficient deep model inferencePattern Recognition, 2020
- A robust iris localization scheme for the iris recognitionMultimedia Tools and Applications, 2020
- Multimodal feature fusion for CNN-based gait recognition: an empirical comparisonNeural Computing and Applications, 2020
- Batch Size Influence on Performance of Graphic and Tensor Processing Units During Training and Inference Phases2019
- Value-Aware Quantization for Training and Inference of Neural Networks2018
- The TUM Gait from Audio, Image and Depth (GAID) database: Multimodal recognition of subjects and traitsJournal of Visual Communication and Image Representation, 2014
- Determining optical flowArtificial Intelligence, 1981