Object tracking for video and camera image capturing becomes more popular in recent scientific and application domain. Many Scientists in Image Processing try to find an efficient and accurate way to track the objects' moving in real time video applications. Particle Swarm Optimization is one of the most efficient and potential approaches developed to provide linear and non-linear object tracking by identifying special patterns for selected object, and achieving efficient algorithm to calculate random object moving. Compare to classic Kalman Filter, Particle Filter, or other improved PSO, this paper is aim to find a more efficient and precious pathway using categorized particle movement with dynamic inertia weight value in PSO to build a tracking procedure in order to provide better tracking speed and quality result in different types of video records and different visions of object moving. The proposed Categorized PSO based target tracking scheme can achieve better quality when compared to Particle Filter and typical Particle Swarm Optimization methods in our tracking experiments. It has been developed in C++ environment and tested against videos to demonstrate its excellent tracking ability in object retrieval and high accurate in tracking objects movement within other similar object's environment.

Small object detection represents a pivotal sub-domain within the field of computer vision. Previous research aimed at enhancing detection accuracy has included augmenting the head layer, refining multi-layer feature pooling techniques, incorporating attention mechanisms, and optimizing loss functions. Despite these efforts, issues such as false negatives and classification ambiguities persist, leading to suboptimal outcomes. To solve these issues, DKA-YOLO is proposed as a new model focusing on improving convolution kernel structures. We develop novel modules based on the concept of dilation kernels aggregation convolution, integrate them into the robust and advanced YOLOv8 framework, and apply the enhanced model to small object detection tasks. The proposed modules include the large size dilation kernels aggregation convolution for the backbone layer, which combines large kernel sizes with dilation convolution structure, and utilizes extensive receptive fields to improve detailed feature extraction. Additionally, the multi-scale dilation kernels aggregation convolution is introduced in the neck layers to enhance performance and efficiency with a diverse set of kernels. Finally, the model’s head layer employs multi-scale convolution kernels detect to enhance feature expression diversity, generalization ability, and computational efficiency of detection. Experimental validation on public datasets demonstrates a significant improvement in detection accuracy by our method, with an increase in mean average precision by 1.5% on the VisDrone and 1.15% on the UAVDT compared to advanced previous methods. Our method also surpasses other previous models in comparative experiments, highlighting its superiority and robustness.

Neural network pruning is essential for deploying deep learning models on resource-constrained devices by reducing computational and memory demands. In this paper, we propose a novel pruning framework, Entropy-Guided Search Space Optimization for Efficient Neural Network Pruning, which uses information entropy to assess the importance of convolutional layers. Specifically, we calculate the layer-wise entropy of pretrained weights, apply outlier detection to remove extreme values, and normalize the entropy values. These normalized values guide the selection of retention ratios, ensuring that layers with higher entropy retain more filters. By refining the subnetwork search space, our approach enhances the efficiency of the search process and improves overall subnetwork performance. The refined search space targets more promising regions, reducing computational overhead and resulting in higher-quality pruned networks. Through iterative optimization, the optimal subnetwork is identified and fine-tuned to produce the final pruned model. Experimental results on benchmark datasets show that our method significantly outperforms existing pruning methods, achieving substantial improvements in both accuracy and computational efficiency. This entropy-guided pruning strategy provides a robust and effective solution for neural network compression, suitable for a wide range of deep learning applications.