One of the most basic and difficult areas of computer vision and image understanding applications is still object detection. Deep neural network models and enhanced object representation have led to significant progre...One of the most basic and difficult areas of computer vision and image understanding applications is still object detection. Deep neural network models and enhanced object representation have led to significant progress in object detection. This research investigates in greater detail how object detection has changed in the recent years in the deep learning age. We provide an overview of the literature on a range of cutting-edge object identification algorithms and the theoretical underpinnings of these techniques. Deep learning technologies are contributing to substantial innovations in the field of object detection. While Convolutional Neural Networks (CNN) have laid a solid foundation, new models such as You Only Look Once (YOLO) and Vision Transformers (ViTs) have expanded the possibilities even further by providing high accuracy and fast detection in a variety of settings. Even with these developments, integrating CNN, YOLO and ViTs, into a coherent framework still poses challenges with juggling computing demand, speed, and accuracy especially in dynamic contexts. Real-time processing in applications like surveillance and autonomous driving necessitates improvements that take use of each model type’s advantages. The goal of this work is to provide an object detection system that maximizes detection speed and accuracy while decreasing processing requirements by integrating YOLO, CNN, and ViTs. Improving real-time detection performance in changing weather and light exposure circumstances, as well as detecting small or partially obscured objects in crowded cities, are among the goals. We provide a hybrid architecture which leverages CNN for robust feature extraction, YOLO for rapid detection, and ViTs for remarkable global context capture via self-attention techniques. Using an innovative training regimen that prioritizes flexible learning rates and data augmentation procedures, the model is trained on an extensive dataset of urban settings. Compared to solo YOLO, CNN, or ViTs models, the suggested model exhibits an increase in detection accuracy. This improvement is especially noticeable in difficult situations such settings with high occlusion and low light. In addition, it attains a decrease in inference time in comparison to baseline models, allowing real-time object detection without performance loss. This work introduces a novel method of object identification that integrates CNN, YOLO and ViTs, in a synergistic way. The resultant framework extends the use of integrated deep learning models in practical applications while also setting a new standard for detection performance under a variety of conditions. Our research advances computer vision by providing a scalable and effective approach to object identification problems. Its possible uses include autonomous navigation, security, and other areas.展开更多
针对传统目标识别方法需要人工设计特征工程,费时费力,泛化性能差的缺点,以YOLO算法和tiny-yolo模型为基础,在tiny-yolo的基础上增加了3×3卷积层和NIN(Network in Net Work)卷积层,设计了一个包含15个卷积层的神经网络模型m-yolo。...针对传统目标识别方法需要人工设计特征工程,费时费力,泛化性能差的缺点,以YOLO算法和tiny-yolo模型为基础,在tiny-yolo的基础上增加了3×3卷积层和NIN(Network in Net Work)卷积层,设计了一个包含15个卷积层的神经网络模型m-yolo。在voc2007和voc2012数据集上的实验结果表明,m-yolo模型提高了识别的准确性和定位的精确性,并且保证了在识别速度上与tiny-yolo基本保持一致,平均识别时间仅上升了0. 6 ms。展开更多
基金The Natural Science Foundation of Jiangsu Province(No.BK20230956)the Jiangsu Funding Program for Excellent Postdoctoral Talents(No.2022ZB188)the Transportation Technology Plan Project of Jiangsu Province(No.2020QD28).
文摘One of the most basic and difficult areas of computer vision and image understanding applications is still object detection. Deep neural network models and enhanced object representation have led to significant progress in object detection. This research investigates in greater detail how object detection has changed in the recent years in the deep learning age. We provide an overview of the literature on a range of cutting-edge object identification algorithms and the theoretical underpinnings of these techniques. Deep learning technologies are contributing to substantial innovations in the field of object detection. While Convolutional Neural Networks (CNN) have laid a solid foundation, new models such as You Only Look Once (YOLO) and Vision Transformers (ViTs) have expanded the possibilities even further by providing high accuracy and fast detection in a variety of settings. Even with these developments, integrating CNN, YOLO and ViTs, into a coherent framework still poses challenges with juggling computing demand, speed, and accuracy especially in dynamic contexts. Real-time processing in applications like surveillance and autonomous driving necessitates improvements that take use of each model type’s advantages. The goal of this work is to provide an object detection system that maximizes detection speed and accuracy while decreasing processing requirements by integrating YOLO, CNN, and ViTs. Improving real-time detection performance in changing weather and light exposure circumstances, as well as detecting small or partially obscured objects in crowded cities, are among the goals. We provide a hybrid architecture which leverages CNN for robust feature extraction, YOLO for rapid detection, and ViTs for remarkable global context capture via self-attention techniques. Using an innovative training regimen that prioritizes flexible learning rates and data augmentation procedures, the model is trained on an extensive dataset of urban settings. Compared to solo YOLO, CNN, or ViTs models, the suggested model exhibits an increase in detection accuracy. This improvement is especially noticeable in difficult situations such settings with high occlusion and low light. In addition, it attains a decrease in inference time in comparison to baseline models, allowing real-time object detection without performance loss. This work introduces a novel method of object identification that integrates CNN, YOLO and ViTs, in a synergistic way. The resultant framework extends the use of integrated deep learning models in practical applications while also setting a new standard for detection performance under a variety of conditions. Our research advances computer vision by providing a scalable and effective approach to object identification problems. Its possible uses include autonomous navigation, security, and other areas.
文摘针对传统目标识别方法需要人工设计特征工程,费时费力,泛化性能差的缺点,以YOLO算法和tiny-yolo模型为基础,在tiny-yolo的基础上增加了3×3卷积层和NIN(Network in Net Work)卷积层,设计了一个包含15个卷积层的神经网络模型m-yolo。在voc2007和voc2012数据集上的实验结果表明,m-yolo模型提高了识别的准确性和定位的精确性,并且保证了在识别速度上与tiny-yolo基本保持一致,平均识别时间仅上升了0. 6 ms。
