Abstract
Artificial intelligence has experienced two cold winters. As algorithms based on deep learning have entered people's sight, target detection technology has also ushered in a leaping development. Compared with other algorithms, the SSD algorithm has very obvious advantages in detection speed and accuracy. This algorithm only runs detection at the top level, which has very high feasibility. Background interference often occurs in pedestrian detection, and there is also the problem of missed detection of small targets. The main research content of the thesis has three parts: the improvement of the original SSD algorithm and the discussion of the basic composition and characteristics of the neural network; changing the basic vgg16 of the original SSD algorithm to resnet50 can improve the detection speed and accuracy.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
