Garage pedestrian detection method based on improved EffecientDet model

A pedestrian detection and model technology, applied in the field of target detection, can solve the complex and changeable garage environment and other problems, achieve the effect of enhancing learning ability, increasing receptive field, and reducing memory cost

Active Publication Date: 2021-03-12
徐州瑞马智能技术有限公司
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the garage environment is complex and changeable, and the detection target has its uniqueness. Directly using EfficientDet to train the target detecto

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
  • Garage pedestrian detection method based on improved EffecientDet model
  • Garage pedestrian detection method based on improved EffecientDet model
  • Garage pedestrian detection method based on improved EffecientDet model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0071] This specific embodiment discloses the garage pedestrian detection method based on the improved EfficientDet model, such as Figure 1 to Figure 7 shown, including the following steps:

[0072] S1: Collect images of garage pedestrians in different time periods and lighting environments;

[0073] S2: if figure 1 As shown, the sample input network needs to be preprocessed and data enhanced before training. For the garage pedestrian image, first cut it into a uniform size, then perform horizontal flip (50% probability) and standardization, and finally use the mosaic data enhancement method. Randomly extract 4 images to generate a composite image, and convert the corresponding label data to generate training samples (such as figure 2 shown);

[0074] S3: This article takes EfficientDet-D0 as an example, in the backbone network EfficientNet-b0 (such as image 3 As shown), the feature distribution network CSPNet is introduced to enhance the learning ability of CNN, while ...

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 a garage pedestrian detection method based on an improved Effective Det model, belongs to the technical field of target detection in image processing, and aims to enrich the background information of pedestrian detection by using a mosaic data enhancement method and calculate the data of four images at one time during Batch Normalization calculation. A feature shunt networkCSPNet is introduced into an EfficientNet, so that the learning ability of the CNN is enhanced, the detection accuracy can be maintained while the model is lightened, and the calculation bottleneck and the memory cost are reduced; a spatial pyramid pooling module SPP is introduced to the top of the feature extraction network, the receptive field of the network is increased, and pedestrian detection can be completed accurately and quickly in a complex and changeable garage environment.

Description

technical field [0001] The invention belongs to the technical field of target detection in image processing, in particular to a garage pedestrian detection method based on an improved EfficientDet model. Background technique [0002] The smart three-dimensional garage is an important part of the process of intelligent city construction. It integrates garage parking space reservation, license plate recognition, automatic parking, and pedestrian detection. Among them, the pedestrian detection in the garage is to ensure the safety of pedestrians in the garage. The environment in the garage is complex and changeable, and the pedestrians in the garage must be taken into account when taking off and landing the parking space, so as to ensure that it can only be lifted and lowered without pedestrians. Therefore, the real-time and accuracy of garage pedestrian detection are very important for the deployment of smart three-dimensional garages. [0003] Garage pedestrian detection is...

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
IPC IPC(8): G06K9/00G06K9/54G06K9/62G06N3/04G06T5/50
CPCG06T5/50G06T2207/20221G06V40/20G06V10/20G06V2201/07G06N3/045G06F18/24G06F18/253G06F18/214
Inventor 牛丹李永胜陈夕松许翠红陈善龙刘子璇
Owner 徐州瑞马智能技术有限公司
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