Trinity‐Yolo: High‐precision logo detection in the real world

Abstract

Logo detection has a wide range of applications in the multimedia field, such as video advertising research, brand awareness monitoring and analysis, trademark infringement detection, autonomous driving and intelligent transportation. Compared with other types of images, logo images in the real world have greater diversity in appearance and more complex backgrounds. Therefore, identifying logos from images is a challenge. A strong baseline method Trinity‐Yolo, is proposed, which incorporates attention mechanism, stripe pooling and weighted boxes fusion (WBF) into the state‐of‐the‐art Yolov4 framework for large‐scale logo detection. The attention mechanism improves the feature extraction ability of the deep detection model, the stripe pooling expands the field of view of the model and the weighted boxes fusion enables the model to obtain excellent corrections when outputting the prediction boxes. Trinity‐Yolo can solve the problems of lack of training data, multi‐scale objects and inconsistent bounding‐box regression. On the dataset LogoDet‐3K, the average performance of Trinity‐Yolo is 3% higher than that of Yolov4. Compared with other deep detection models, the performance of Trinity‐Yolo is improved more. The experimental performance on other existing datasets verifies the effectiveness of this method.

MFF-YOLO: An Accurate Model for Detecting Tunnel Defects Based on Multi-Scale Feature Fusion

“…Multi-scale feature fusion is a technique for combining feature maps at different scales to improve the performance of computer vision tasks. Common approaches include cascade structures [ 36 , 37 , 38 ], pyramid networks [ 39 , 40 , 41 , 42 ] and attention mechanisms [ 43 , 44 , 45 ]. Cascade structures link feature maps at different scales together to form cascade networks, which can be effective in improving performance; pyramid networks are a hierarchical approach to image processing that extracts features at different scales and combines them; and attention mechanisms can make the network focus more on important features by weighting feature maps at different scales.…”