Motion feature extraction using magnocellular-inspired spiking neural networks for drone detection
Traditional object detection methods usually underperform when locating tiny or small drones against complex backgrounds, since the appearance features of the targets and the backgrounds are highly similar. To address this, inspired by the magnocellular motion processing mechanisms, we proposed to u...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Computational Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fncom.2025.1452203/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591692306317312 |
|---|---|
| author | Jiayi Zheng Jiayi Zheng Yaping Wan Xin Yang Hua Zhong Minghua Du Gang Wang Gang Wang |
| author_facet | Jiayi Zheng Jiayi Zheng Yaping Wan Xin Yang Hua Zhong Minghua Du Gang Wang Gang Wang |
| author_sort | Jiayi Zheng |
| collection | DOAJ |
| description | Traditional object detection methods usually underperform when locating tiny or small drones against complex backgrounds, since the appearance features of the targets and the backgrounds are highly similar. To address this, inspired by the magnocellular motion processing mechanisms, we proposed to utilize the spatial–temporal characteristics of the flying drones based on spiking neural networks, thereby developing the Magno-Spiking Neural Network (MG-SNN) for drone detection. The MG-SNN can learn to identify potential regions of moving targets through motion saliency estimation and subsequently integrates the information into the popular object detection algorithms to design the retinal-inspired spiking neural network module for drone motion extraction and object detection architecture, which integrates motion and spatial features before object detection to enhance detection accuracy. To design and train the MG-SNN, we propose a new backpropagation method called Dynamic Threshold Multi-frame Spike Time Sequence (DT-MSTS), and establish a dataset for the training and validation of MG-SNN, effectively extracting and updating visual motion features. Experimental results in terms of drone detection performance indicate that the incorporation of MG-SNN significantly improves the accuracy of low-altitude drone detection tasks compared to popular small object detection algorithms, acting as a cheap plug-and-play module in detecting small flying targets against complex backgrounds. |
| format | Article |
| id | doaj-art-3eecc18ae70e4909822d3aa552f5224e |
| institution | Kabale University |
| issn | 1662-5188 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computational Neuroscience |
| spelling | doaj-art-3eecc18ae70e4909822d3aa552f5224e2025-01-22T07:11:23ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882025-01-011910.3389/fncom.2025.14522031452203Motion feature extraction using magnocellular-inspired spiking neural networks for drone detectionJiayi Zheng0Jiayi Zheng1Yaping Wan2Xin Yang3Hua Zhong4Minghua Du5Gang Wang6Gang Wang7Department of Computer, University of South China, Hengyang, ChinaCenter of Brain Sciences, Beijing Institute of Basic Medical Sciences, Beijing, ChinaDepartment of Computer, University of South China, Hengyang, ChinaCenter of Brain Sciences, Beijing Institute of Basic Medical Sciences, Beijing, ChinaDepartment of Computer, University of South China, Hengyang, ChinaDepartment of Emergency, The First Medical Center, Chinese PLA General Hospital, Beijing, ChinaCenter of Brain Sciences, Beijing Institute of Basic Medical Sciences, Beijing, ChinaChinese Institute for Brain Research, Beijing, ChinaTraditional object detection methods usually underperform when locating tiny or small drones against complex backgrounds, since the appearance features of the targets and the backgrounds are highly similar. To address this, inspired by the magnocellular motion processing mechanisms, we proposed to utilize the spatial–temporal characteristics of the flying drones based on spiking neural networks, thereby developing the Magno-Spiking Neural Network (MG-SNN) for drone detection. The MG-SNN can learn to identify potential regions of moving targets through motion saliency estimation and subsequently integrates the information into the popular object detection algorithms to design the retinal-inspired spiking neural network module for drone motion extraction and object detection architecture, which integrates motion and spatial features before object detection to enhance detection accuracy. To design and train the MG-SNN, we propose a new backpropagation method called Dynamic Threshold Multi-frame Spike Time Sequence (DT-MSTS), and establish a dataset for the training and validation of MG-SNN, effectively extracting and updating visual motion features. Experimental results in terms of drone detection performance indicate that the incorporation of MG-SNN significantly improves the accuracy of low-altitude drone detection tasks compared to popular small object detection algorithms, acting as a cheap plug-and-play module in detecting small flying targets against complex backgrounds.https://www.frontiersin.org/articles/10.3389/fncom.2025.1452203/fullbio-inspired vision computationspiking neural networksmotion detectiondrone target recognitionmotion saliency estimationvisual motion features |
| spellingShingle | Jiayi Zheng Jiayi Zheng Yaping Wan Xin Yang Hua Zhong Minghua Du Gang Wang Gang Wang Motion feature extraction using magnocellular-inspired spiking neural networks for drone detection Frontiers in Computational Neuroscience bio-inspired vision computation spiking neural networks motion detection drone target recognition motion saliency estimation visual motion features |
| title | Motion feature extraction using magnocellular-inspired spiking neural networks for drone detection |
| title_full | Motion feature extraction using magnocellular-inspired spiking neural networks for drone detection |
| title_fullStr | Motion feature extraction using magnocellular-inspired spiking neural networks for drone detection |
| title_full_unstemmed | Motion feature extraction using magnocellular-inspired spiking neural networks for drone detection |
| title_short | Motion feature extraction using magnocellular-inspired spiking neural networks for drone detection |
| title_sort | motion feature extraction using magnocellular inspired spiking neural networks for drone detection |
| topic | bio-inspired vision computation spiking neural networks motion detection drone target recognition motion saliency estimation visual motion features |
| url | https://www.frontiersin.org/articles/10.3389/fncom.2025.1452203/full |
| work_keys_str_mv | AT jiayizheng motionfeatureextractionusingmagnocellularinspiredspikingneuralnetworksfordronedetection AT jiayizheng motionfeatureextractionusingmagnocellularinspiredspikingneuralnetworksfordronedetection AT yapingwan motionfeatureextractionusingmagnocellularinspiredspikingneuralnetworksfordronedetection AT xinyang motionfeatureextractionusingmagnocellularinspiredspikingneuralnetworksfordronedetection AT huazhong motionfeatureextractionusingmagnocellularinspiredspikingneuralnetworksfordronedetection AT minghuadu motionfeatureextractionusingmagnocellularinspiredspikingneuralnetworksfordronedetection AT gangwang motionfeatureextractionusingmagnocellularinspiredspikingneuralnetworksfordronedetection AT gangwang motionfeatureextractionusingmagnocellularinspiredspikingneuralnetworksfordronedetection |