Aerial photography car detection method based on YOLOv4

A detection method and car technology, applied in the field of target detection, can solve the problem of large space occupied by training models, and achieve the effects of shortening inference time, reducing the number of parameters, and improving detection accuracy

Pending Publication Date: 2021-04-16
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a YOLOv4-based aerial vehicle detection method, which solves the problem that the YOLOv4 training model takes up a lot of space, and at the same time improves the detection accuracy of small objects in aerial images

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Aerial photography car detection method based on YOLOv4
  • Aerial photography car detection method based on YOLOv4
  • Aerial photography car detection method based on YOLOv4

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] Embodiments of the invention are described in detail below, examples of which are illustrated in the accompanying drawings. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0043] Such as figure 1 As shown, the present invention proposes a method for detecting aerial cars based on YOLOv4, and the specific steps are as follows:

[0044] (1) Create a drone aerial photography data set, label the cars, and convert the label format to YOLO format.

[0045] (2) Configure model parameters according to the data set defined in step (1).

[0046] (3) Select the pre-training weights trained by the darknet version of YOLOv4 on the coco data set, and transfer the data set in step (1) into the YOLOv4 network model for basic training until the number of iterations or convergence is reached, and the model after basic training is obtained .

[0047] (4)...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an aerial photography car detection method based on YOLOv4, and the method comprises the steps: employing a YOLOv4 model of a darknet version, carrying out the labeling of cars with 2000 images in an open source aerial photography data set, arranging the cars into a data set format needed by the YOLOv4, and then employing the YOLOv4 to pre-train a weight to train an own aerial photography data set; L1 loss is used to reduce neural network weight to perform sparse training, a channel pruning technology is used to perform pruning training on YOLOv4, the model is compressed, the training speed is improved, the pruned weight is finely adjusted, and a random multi-scale training technology is used to improve the generalization ability of the training model, so that the precision is improved. And finally, the aerial image test set is tested by using the self-trained weight, so that the memory occupation space is reduced on the premise that the detection speed meets the real-time requirement and the detection precision is not influenced.

Description

technical field [0001] The invention relates to a YOLOv4-based aerial car detection method, which belongs to the technical field of target detection. Background technique [0002] In the field of UAV image processing, target detection is one of the most popular directions nowadays. In view of the characteristics of UAV images such as small targets, large numbers, complex natural environment and easy occlusion of targets, the target detection of UAV aerial images Technology puts forward higher requirements. The traditional target detection algorithm is completed through image preprocessing, sliding window feature extraction, classifier classification, and then feature matching and positioning. Although this method has certain Accuracy, but it takes a certain amount of time and human resources. With the rapid development of the target detection algorithm based on deep learning, more and more target detection models have been proposed. The target detection algorithm under deep...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/04G06N3/08
Inventor 王浩雪曹杰韩玉洁
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap