A Lightweight Deep and Wide Network for Image-Based Detection of Industrial Waste Gas
Top Cited Papers
- 26 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (6) , 7909-7920
Abstract
Due to inadequate monitoring, key pollutants (e.g., PM2.5, VOCs, etc) very possibly leak into atmosphere, thus to endanger the long-term and short-term life safety of people that work and live in the environment. Therefore, it is imperative to effectively and efficiently detect the leakage of industrial waste gas, for the purpose of timely lowering the risk of pollution and explosions. To solve such a problem, we in this paper propose a new lightweight deep and wide network (LdwNet) for detecting the leakage of industrial waste gas from an image, which brings about the two main merits: 1) Compensating for the deficiencies of sensor-based detection methods, which can accurately detect the leakage of waste gas and even measure its concentrations but require to seek leakage sources beforehand; 2) Overcoming the shortcomings of image-based detection methods, which leverage DNN-based recognition technologies and usually suffer from low efficacy, low efficiency and high energy consumption during the model training and inference. To specify, the proposed LdwNet is developed by simulating human perception, motivated by the method which detects the leakage of industrial waste gas from surveillance images with the human observation and judgement. First, based on the inspiration that the human eyes are highly sensitive to horizontal and vertical stimuli, we construct a novel lightweight parallel-series-stripe (PS2) module to validly extract features with very few parameters. Second, to fully exploit deep and shallow features for fusing the global and local information, we extend the PS2 module as a backbone along both the deep and wide directions to build the multi-channel network. Third, to achieve effective, efficient and low-carbon detection in model running, we constraint the extended PS2 modules with parameter sharing to prodigiously reduce the model parameters and thus to make the proposed model ultra-lightweight. Experiments on the datasets of carbon particulate matters and ethylene leakage prove that our LdwNet with ten thousand parameters outperforms the state-of-the-art models with millions of parameters in detection accuracy and implementation cost, and this renders our proposed LdwNet more suitable for real industrial applications.Keywords
Funding Information
- National Key Research and Development Program of China (2024YFE0100500)
- National Natural Science Foundation of China (62322302)
- National Natural Science Foundation of China (62273011)
- National Natural Science Foundation of China (62225112)
- National Natural Science Foundation of China (62431015)
This publication has 49 references indexed in Scilit:
- Reinforcement learning for single-agent to multi-agent systems: from basic theory to industrial application progress, a surveyArtificial Intelligence Review, 2025
- A lightweight network enhanced by attention-guided cross-scale interaction for underwater object detectionApplied Soft Computing, 2025
- Unsupervised image stitching based on Generative Adversarial Networks and feature frequency awareness algorithmApplied Soft Computing, 2025
- Semantic Masking with Curriculum Learning for Robust HDR Image ReconstructionInternational Journal of Computer Vision, 2025
- Safe optimal robust control of nonlinear systems with asymmetric input constraints using reinforcement learningApplied Intelligence, 2023
- Combining Transformer and Convolutional Neural Network for Smoke Detection2023
- ScalableViT: Rethinking the Context-Oriented Generalization of Vision Transformer2022
- Adaptive Token Sampling for Efficient Vision Transformers2022
- Visualizing and Understanding Convolutional Networks2014
- Lung Cancer, Cardiopulmonary Mortality, and Long-term Exposure to Fine Particulate Air PollutionJAMA, 2002