Target detection method and device and storage medium
A target detection and target technology, applied in image data processing, instrumentation, computing, etc., can solve problems such as inability to detect large-area occlusion and complete occlusion, the model lacks the ability to detect occluded objects, and difficult to train sample coverage.
Active Publication Date: 2021-03-02
马鞍山市瀚海云星科技有限责任公司
View PDF11 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] However, in practical applications, the occlusion noise is complex and diverse, and it is difficult to completely cover it when making training samples, resulting in the model lacking the ability to detect occluded objects (that is, occluded targets)
The image registration scheme can solve some occluded situations, but cannot detect large-area occlusions and complete occlusions (such as large-scale cranes in industrial sites occluding targets)
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
[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of them. 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.
[0021] The flow charts shown in the drawings are just illustrations, and do not necessarily include all contents and operations / steps, nor must they be performed in the order described. For example, some operations / steps can be decomposed, combined or partly combined, so the actual order of execution may be changed according to the actual situation.
[0022] The industrial production environment often requires the use of object detection technology to detect specif...
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 discloses a target detection method and device and a storage medium, and the method comprises the steps: obtaining a current image frame which comprises a related object image; registering the current image frame by using a related object image of the related image frame to obtain a registration mapping relationship of the related object image, the related image frame comprising a target image and a related object image, the relative position between the target and the related object being unchanged, and the relative position between the target and the related object being unchanged; wherein the target and the related object are within the visual angle range of the camera device when the camera device shoots to obtain the current image frame and the related image frame; and obtaining a registration position of the target image of the related image frame in the current image frame according to the registration mapping relationship and each pixel of the target image of therelated image frame. Through the mode, the position of the target in the image frame can be detected, and even if the target is partially shielded, the target is completely shielded or the light is dark.
Description
technical field [0001] The present application relates to the technical field of image detection, in particular to an object detection method, device and storage medium. Background technique [0002] The industrial production environment often requires the use of object detection technology to detect specific objects (ie, targets) in the video of the on-site camera. For example, in a steel plant environment, it is necessary to detect the unloading truck to locate the goods on the truck and perform data analysis tasks such as weight prediction based on the cargo data. In the industrial production environment, cameras can be deployed to capture industrial environments, and then computer algorithm models can be used to analyze the captured videos. At present, deep learning models have been widely used in the fields of computer vision and natural language processing due to their powerful fitting capabilities. Among the many models of deep learning, the yolo model performs well...
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 IPC IPC(8): G06T7/00G06T3/00G06T7/33
CPCG06T7/0004G06T7/33G06T2207/10016G06T3/147
Inventor 彭焯艺孙军欢胡水海
Owner 马鞍山市瀚海云星科技有限责任公司