Obstacle missing detection repairing method and device, equipment and storage medium
A repair method and obstacle technology, applied in the direction of neural learning methods, biological neural network models, instruments, etc., can solve the problems of large resource consumption, large time cost and labor cost, and the inability to quickly solve the problems of missed detection of obstacles. The effect of missed detection problems
Pending Publication Date: 2021-07-09
ZHEJIANG GEELY HOLDING (GROUP) CO LTD +1
View PDF17 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] This application provides a method, device, equipment, and storage medium for repairing missed detection of obstacles, which are used to solve the problem of missing detection of obstacles that needs to be invested in a large amount of time and labor costs in the prior art, consumes a lot of resources, and cannot be quickly solved
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0051] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the accompanying drawings in this application. Obviously, the described embodiments are part of the embodiments of this application , but not all examples. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.
[0052] In the automotive industry, autonomous driving technology is currently the hottest research field. It can not only help auto companies take the lead and industry advantages, but also benefit the general public with this new convenient and safe way of travel. In the construction of L4-level unmanned driving systems, the sensor configuration solutions are usually cameras, laser radars, and millimeter-wave rad...
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
Login to View More Abstract
The invention provides an obstacle missing detection repairing method, device and equipment and a storage medium, and the method comprises the steps of obtaining a plurality of anchor frames and obstacle image features outputted by a tail end feature output layer of a preset model, and the preset model comprises a plurality of feature output layers; and according to the plurality of anchor frame and obstacle image features, obtaining a category feature map and a foreground and background feature map of each anchor frame; determining a missing detection target feature map and a to-be-processed feature map according to the category feature map and the foreground and background feature map of each anchor frame; and strengthening the to-be-processed feature map according to the missing detection target feature map. On the premise of not modifying a model framework, not increasing a large amount of missing detection obstacle data and not retraining the model, based on the relationship between the obstacle category and the anchor frame, the output of the specific foreground and background feature map is enhanced, and the missing detection problem is effectively and quickly solved.
Description
technical field [0001] This application relates to the technical field of automatic driving, and proposes a method, device, equipment, and storage medium for missed detection and repair of obstacles. Background technique [0002] L4 driverless cars usually use multiple cameras covering a 360° view of front, rear, left, and right to detect obstacles around the car. When the current visual detection model is applied to driverless cars, obstacles will be missed. [0003] The solution to the problem of missed obstacle detection usually includes: 1. Modify the framework of the visual inspection model to enhance the feature extraction capability of the model; Make the visual detection model have the ability to identify the obstacle. [0004] However, modifying the model framework and collecting missed obstacle detection data requires a lot of time and labor costs, which consumes a lot of resources and cannot quickly solve the problem of missed obstacle detection. Contents of t...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/58G06V10/44G06N3/045G06F18/23
Inventor 郭雅婵张立志周磊
Owner ZHEJIANG GEELY HOLDING (GROUP) CO LTD