Abstract
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.
Highlights
Unmanned aerial vehicles (UAV) have played an important role in traffic monitoring, route inspection, military, forestry [1,2,3,4], and other fields in recent years
Comparison of Different Network Architectures. This experiment compares SMYOLO with three other advanced target detection algorithms and calculates the parameter size and inference speed of each model to verify the effectiveness of SMYOLO
Compared with the original model YOLOv4, SMYOLO has reduced the parameter amount by 81%, the model size has been reduced by 76.90%, and the inference speed has increased by 43.29%
Summary
Unmanned aerial vehicles (UAV) have played an important role in traffic monitoring, route inspection, military, forestry [1,2,3,4], and other fields in recent years. Pedestrian detection is becoming more and more important in applications such as intelligent monitoring, re-identification of people, and autonomous driving. The target detection algorithm based on deep learning uses a convolutional neural network (CNN) to extract the target feature richly to complete target detection. The current target detection methods based on deep learning have achieved specific achievements, there are still significant challenges in pedestrian detection in unique low-altitude drone scenes.
Published Version (Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.