TensorRT acceleration based on deep learning photoelectric target detection

One of the important research directions in the field of target detection in computer vision, among which deep learning-based target detection can extract advanced features and has higher detection accuracy than traditional detection algorithms. The inference speed of convolutional neural networks in embedded platforms is low, and the practical application value is low. Therefore, for the background of optoelectronic device detection and camera detection, on the embedded platform NVIDIA Jeston Nano, the ResNet18 convolutional neural network is used to identify the photoelectric target. Use TensorRT to accelerate the process of network model simplification and engine construction, and accelerate the network inference time. Experimental results show that when the input image resolution is 640*480, the inference time of tensorRT technology after running the network on the NVIDIA Jeston Nano device is in the range of 0.04-0.06s, and the single-area photoelectric target detection inference is accelerated by 2.38 times and the multi-area photoelectric target detection inference is accelerated by 2.74 times, which provides support for practical applications.