Unlock instant, AI-driven research and patent intelligence for your innovation.

A fast pedestrian detection method based on neural network

A technology of pedestrian detection and neural network, which is applied in the directions of instruments, calculations, character and pattern recognition, etc., can solve the problems of slow detection speed of pedestrians, achieve the effects of enhanced detection accuracy, strong practicability, and increased speed

Active Publication Date: 2020-01-31
NORTHWEST UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] Aiming at the shortcomings of the existing pedestrian detection process, the present invention proposes a fast pedestrian detection method based on neural network, which effectively solves the shortcoming of slow pedestrian detection

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
  • A fast pedestrian detection method based on neural network
  • A fast pedestrian detection method based on neural network
  • A fast pedestrian detection method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Step 1, collect a color image from the camera, and the resolution of the collected image is 640x480. like figure 1 Shown is a frame of picture collected from the camera. A general color image contains three channels (red, green and blue), and only one of the channels is shown here.

[0045] 1. Extract images from video streams;

[0046] The method for obtaining pictures from the video stream in this embodiment is to call the method cvCaptureFromCAM() in the library function of OPENCV. The pointer of the camera can be obtained through cvCaptureFromCAM(). Let the acquired camera pointer be cap. Then create two threads: Fetch_thread, Detect_thread. Fetch_thresh is used to grab the data in the camera and store it as an image matrix. Detect_thread is used to detect pedestrians and output the final detection results to the image.

[0047] In Fetch_thresh, the cvQueryFrame(cap) method in the OPENCV library function is first called to synchronize the data in the camera a...

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 fast pedestrian detection method based on a neural network. The method aims at the shortcomings of the existing pedestrian detection process, and proposes a fast pedestrian detection method based on a neural network. This method proposes a new detection process, which effectively solves the shortcoming of slow pedestrian detection. Since the detection process of this method is to detect pedestrians, the network only propagates forward once, and there is no need to repeatedly extract features from the feature map, so the detection speed of this method can reach 42 images per second.

Description

technical field [0001] The invention belongs to the problem of pedestrian safety in the field of unmanned driving of automobiles, and uses a neural network to detect pedestrians, thereby providing a basis for unmanned driving to protect the life safety of pedestrians. Background technique [0002] With the development of artificial intelligence, various new technologies and applications emerge in an endless stream. People pay more and more attention to the "line" in "basic clothing, housing, and transportation". The emergence of "Didi Taxi" has enriched the way people travel. And unmanned driving technology is another hot spot that people and researchers pay attention to. Unmanned driving is also called autonomous driving. Baidu, Google, Tesla and other companies are vigorously developing driverless cars. In autonomous driving, the core issues are pedestrian detection and vehicle detection methods. Because the quality of pedestrian detection and vehicle detection is the...

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 Patents(China)
IPC IPC(8): G06K9/00
CPCG06V40/103
Inventor 彭进业胡洋王珺李展祝轩王琳文才艾娜
Owner NORTHWEST UNIV