To solve the problems in online target detection on the embedded platform, such as high missed detection rate, low accuracy, and slow speed, a lightweight target recognition method of MobileNetv3-CenterNet is proposed. This method combined the anchor-free Centernet network with the MobileNetv3 small network and trained on the UA-DETRAC and PASCAL VOC07 + 12 standard datasets. While reducing the scale of the network model, the MobileNetv3-Centernet model shows a good balance in the accuracy and speed of target recognition and effectively solves the problem of missing detection of dense and small targets in online detection. To verify the recognition performance of the model, it is tested on 2683 images of the UA- DETRAC and PASCAL VOC 2007 datasets, and compared with the analysis results of CenterNet-DLA34, CenterNet-ResNet18, CenterNet-MobileNetv3-large, YOLOv3, MobileNetv2-YOLOv3, SSD, MobileNetv2-SSD and Faster R-CNN models. The results show that the MobileNetv3-CenterNet model accurately recognized the dense targets and small targets missed by other methods, and obtains a recognition accuracy of 99.4% with a running speed of FPS53. The comprehensive detection effect of MobileNetv3-CenterNet is better than other methods. The MobileNetv3-CenterNet lightweight target recognition method will provide effective technical support for the target recognition of deep learning networks in embedded platforms and online detection.