Volume 96
Published on October 2024Volume title: Proceedings of CONF-MLA Workshop: Mastering the Art of GANs: Unleashing Creativity with Generative Adversarial Networks
Object detection is a crucial and challenging task in computer vision. With advancements in deep learning technology, YOLOv3 has become a widely adopted and efficient object detection algorithm. However, YOLOv3 encounters challenges when managing complex scenes and detecting small objects. To tackle these challenges, this research introduces an enhanced YOLOv3 architecture incorporating the Squeeze-and-Excitation (SE) module to improve feature representation capabilities. The SE module captures the interdependencies between channels and dynamically adjusts their feature responses, enhancing the model’s representation capability. By integrating the SE module into YOLOv3, this study seeks to substantially improve the model’s effectiveness in complex scenes and small object detection. Experimental results indicate that the enhanced YOLOv3 surpasses the original model on the COCO2017 dataset, validating the effectiveness of this method. Additionally, the improved architecture further enhances detection accuracy and robustness while maintaining efficient detection speed. The contribution of this study lies in proposing an effective feature enhancement method, introducing innovative concepts and techniques for object detection.
In the realm of robotics and autonomous systems, path planning is a pivotal component that determines the efficacy and safety of navigational tasks. With the proliferation of autonomous vehicles, drones, and mobile robots, the need for efficient and adaptive path planning algorithms has become increasingly acute. This paper studies AStar, LPA and DStarLite path planning algorithms based on Matlab platform, and compares their performance through simulation experiments. AStar algorithm is simple and widely applicable, but it has some shortcomings in path smoothness and computational efficiency. LPA improves path smoothness by introducing dynamic cost updating, but it may sacrifice some computational efficiency. The DStarLite algorithm performs well in dynamic environments with an efficient incremental update strategy that maintains high path smoothness and low computational costs. The experimental results show that DStarLite is the fastest in most cases, LPA* and DStarLite are superior to AStar in path smoothness. Future research may explore combining the advantages of each algorithm to develop more efficient, flexible and robust path planning algorithms to cope with complex and changeable actual scenarios.
The image generation based on deep learning is a technology that can generate new images or outpaint old images or improve visual effect of old images through learning from input data, according to deep learning structure. The representative technologies of image generation are image outpainting and image super-resolution. Deep learning is widely utilized in the field of computer vision. Facing different needs, it is essential to choose proper ways. This essay reviews several representative and new methods of image outpainting and image super-resolution. Compared with the results generated by old methods, the results generated by new image outpainting methods introduced in this essay have greater precision and clarity, the methods of image super-resolution that are suitable for all fields and professional fields can learn from each other’s dataset manually to train and develop. There is still unimaginable prospect of deep learning in the field of image outpainting and image super-resolution. Therefore, it is worthy of attention.