The development of intelligent manufacturing often focuses on production flexibility, customization and quality control, which are crucial for chip manufacturing. Specifically, defect detection and classification are important for manufacturing processes in the semiconductor and electronics industries. The intelligent detection methods of chip defects are still challenge and have always been a particular concern of chip processing manufactures in an automated industrial production line. YOLOv4 method has been widely used for object detection due to its accuracy and speed. However, there are still difficulties and challenges in the detection for small targets, especially defects on chip surface. This study proposed a small object detection method based on YOLOv4 for small object in order to improve the performance of detection. It includes expanding feature fusion of shallow features; using k-means++ clustering to optimize the number and size of anchor box; and removing redundant YOLO head network branches to increase detection efficiency. The results of experiments reflect that SO-YOLO is superior to the original YOLOv4, YOLOv5s, and YOLOv5l models in terms of the number of parameters, classification and detection accuracy.

No abstract

The research on video analytics especially in the area of human behavior recognition has become increasingly popular recently. It is widely applied in virtual reality, video surveillance, and video retrieval. With the advancement of deep learning algorithms and computer hardware, the conventional two-dimensional convolution technique for training video models has been replaced by three-dimensional convolution, which enables the extraction of spatio-temporal features. Specifically, the use of 3D convolution in human behavior recognition has been the subject of growing interest. However, the increased dimensionality has led to challenges such as the dramatic increase in the number of parameters, increased time complexity, and a strong dependence on GPUs for effective spatio-temporal feature extraction. The training speed can be considerably slow without the support of powerful GPU hardware. To address these issues, this study proposes an Adaptive Temporal Compression (ATC) module that serves as a standalone module and can be integrated into existing architectures. The ATC module effectively reduces GPU computing load and time complexity with negligible loss of accuracy, thereby facilitating real-time human behavior recognition.

Multi-object tracking (MOT) algorithms are typically classified as one-shot or two-step algorithms. The one-shot MOT algorithm is widely studied and applied due to its fast inference speed. However, one-shot algorithms include two sub-tasks of detection and re-ID, which have conflicting directions for model optimization, thus limiting tracking performance. Additionally, MOT algorithms often suffer from serious ID switching issues, which can negatively affect the tracking effect. To address these challenges, this study proposes the DETrack algorithm, which consists of feature decomposition and feature enhancement modules. The feature decomposition module can effectively exploit the differences and correlations of different tasks to solve the conflict problem. Moreover, it can effectively mitigate the competition between the detection and re-ID tasks, while simultaneously enhancing their cooperation. The feature enhancement module can improve feature quality and alleviate the problem of target ID switching. Experimental results demonstrate that DETrack has achieved improvements in multi-object tracking performance, while reducing the number of ID switching. The designed method of feature decomposition and feature enhancement can significantly enhance target tracking effectiveness.