An improved Tiny YOLOv3 for real-time object detection

The existing real-time object detection algorithm often omits the objects in the object detection. So an improved Tiny YOLOv3 (you look only once) algorithm is proposed with both lightweight and high accuracy of object detection. The improved Tiny YOLOv3 uses K-means clustering to estimate the size of the anchor boxes for dataset. The pooling and convolution layers are added in the network to strengthen feature fusion and reduce parameters. The network structure increases upsampling and downsampling to enhance multi-scale fusion. The complete intersection over union is added in the loss function, which effectively improves the detection results. In addition, the proposed method has the lightweight module size and can be trained in the CPU. The experimental results show that the proposed method can meet the requirements of the detection speed and accuracy.

Automated summary

The improved Tiny YOLOv3 algorithm leverages K-means clustering, pooling, convolution layers, and upsampling/downsampling techniques to enhance feature fusion and multi-scale fusion, ultimately incorporating complete intersection over union in the loss function for improved detection results. It is lightweight and can be trained on a CPU, meeting the requirements of detection speed and accuracy.