KEYWORDS: Object detection, Detection and tracking algorithms, Target detection, Evolutionary algorithms, Computer vision technology, Education and training, Deep learning, Data modeling, Small targets, Pattern recognition
YOLOv5 has been improved to solve the problems such as low speed and accuracy of pedestrian detection task and insufficient feature fusion in complex scenarios. First, the GhostBottleneck module replaces the existing BottleneckCSP submodule for algorithm backbone networks, which improves the detection speed. Then, CBMA module is introduced to make the model enhance the ability of accurate positioning of small targets to improve target detection capability. Finally, SIoU_loss is used as the boundary box regression loss function to effectively predict the distance between the boundary box and the real boundary box, and improve the detection accuracy of the algorithm. The experimental results indicate that the improved algorithm can effectively improve the accuracy of pedestrian target detection.
Aiming at the problems of locating and identifying impediment for minor targets as well as unpromising detection accuracy, a traffic sign detection algorithm based on improved YOLOv5 is propounded in this paper. First, the Addition of the Coordinate Attention Mechanism module behind the backbone network enables the model to effectively capture the relationship between location information and channels, thereby more accurately locates the area of interest. Then a detection layer is introduced into the network structure, and the feature map is continued to be upsampled after the 17th layer of the original algorithm network structure, so that the feature map continues to expand, and a feature map of 160 *160 size is obtained at the 19th layer and the feature map of the second layer of the backbone network is spliced and integrated. This results in a larger feature map for the detection of small targets. Finally, α -CIoU loss is used to replace the original CIoU positioning loss function in the model training stage to obtain higher quality anchor frame. Experiments are performed on the TT100K dataset, compared to the original YOLOv5 algorithm, the proposed algorithm improves accuracy by 3.9%, recall rate by 5.5% and mAP by 4.6% under the premise of less speed reduction, which still meets the requirements of real-time detection.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.