SMYOLO: Lightweight Pedestrian Target Detection Algorithm in Low-Altitude Scenarios

Future Internet

Xin Ma¹  Ming Ji¹  Weiwei Zhang¹  Chenghui Zhen¹  Yuzhao Zhang¹ 

[1]College of Engineering, Huaqiao University, Quanzhou 362021, China

关键词: model compression;    pedestrian detection;    deep learning;    drone scene;   

DOI  :  10.3390/fi14010021

来源: DOAJ

【 摘 要 】

Due to the arbitrariness of the drone’s shooting angle of view and camera movement and the limited computing power of the drone platform, pedestrian detection in the drone scene poses a greater challenge. This paper proposes a new convolutional neural network structure, SMYOLO, which achieves the balance of accuracy and speed from three aspects: (1) By combining deep separable convolution and point convolution and replacing the activation function, the calculation amount and parameters of the original network are reduced; (2) by adding a batch normalization (BN) layer, SMYOLO accelerates the convergence and improves the generalization ability; and (3) through scale matching, reduces the feature loss of the original network. Compared with the original network model, SMYOLO reduces the accuracy of the model by only 4.36%, the model size is reduced by 76.90%, the inference speed is increased by 43.29%, and the detection target is accelerated by 33.33%, achieving minimization of the network model volume while ensuring the detection accuracy of the model.

【 授权许可】

Unknown