article · World Electric Vehicle Journal
Detecting moving objects is critical for intelligent transportation systems and video surveillance. While deep convolutional neural networks offer high accuracy, they typically require extensive manual data labelling, substantial computing power, and struggle to adapt across diverse scenes. To address these limitations, a framework pairs classical background subtraction with a modified YOLOv4 neural network for unsupervised detection. The approach first isolates moving items via low-rank decomposition and refines them using clustering. These refined outputs generate automated labels directly from video footage using motion information, removing the need for manual annotation. The resulting data fine-tunes the modified YOLOv4 model for subsequent object detection and classification tasks. Evaluated on standard benchmark datasets, CDnet 2014 and UA-DETRAC, this combined method achieves a substantial increase in mean average precision over existing state-of-the-art systems.
Manual labelling of video data is expensive, slow, and limits how quickly intelligent monitoring systems can adapt to new locations. By generating its own training annotations directly from raw video motion, this approach enables automated vision systems to operate effectively in new environments with lower computational demands, improving the feasibility of real-time monitoring in transport networks and security contexts.
This technology could benefit developers of intelligent transportation systems and video surveillance software by cutting the labour and costs associated with manual data annotation. The research sits at an applied and tested stage, having been validated against real-world benchmark datasets rather than deployed in commercial production. Moving towards real-world deployment would require testing on live video feeds across varying operational hardware.
AI-generated from the published abstract. Always read the original work before citing.
Moving object detection is a vital research area that plays an essential role in intelligent transportation systems (ITSs) and various applications in computer vision. Recently, researchers have utilized convolutional neural networks (CNNs) to develop new techniques in object detection and recognition. However, with the increasing number of machine learning strategies used for object detection, there has been a growing need for large datasets with accurate ground truth used for the training, usually demanding their manual labeling. Moreover, most of these deep strategies are supervised and only applicable for specific scenes with large computational resources needed. Alternatively, other object detection techniques such as classical background subtraction need low computational resources and can be used with general scenes. In this paper, we propose a new a reliable semi-automatic method that combines a modified version of the detection-based CNN You Only Look Once V4 (YOLOv4) technique and background subtraction technique to perform an unsupervised object detection for surveillance videos. In this proposed strategy, background subtraction-based low-rank decomposition is applied firstly to extract the moving objects. Then, a clustering method is adopted to refine the background subtraction (BS) result. Finally, the refined results are used to fine-tune the modified YOLO v4 before using it in the detection and classification of objects. The main contribution of this work is a new detection framework that overcomes manual labeling and creates an automatic labeler that can replace manual labeling using motion information to supply labeled training data (background and foreground) directly from the detection video. Extensive experiments using real-world object monitoring benchmarks indicate that the suggested framework obtains a considerable increase in mAP compared to state-of-the-art results on both the CDnet 2014 and UA-DETRAC datasets.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/wevj15060255
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
