Binocular vision real-time perception and positioning method, system and device for marine product fetching
A technology of binocular vision and positioning method, applied in the field of computer vision, can solve the problems of tracking failure and insufficient positioning accuracy of seafood perception, and achieve the effect of improving accuracy and reliability, excellent detection performance, detection accuracy and detection failure.
Active Publication Date: 2019-09-13
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF7 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem that the positioning accuracy of seafood perception is not enough to cause tracking failure, the first aspect of the present invention proposes a binocular vision real-time perception positioning method for grasping seafood. include:
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
[0046] In order to make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not All examples. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0047] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the related invention, but not to limit the invention. In addition, it should be noted that, for the convenience of description, only the parts related to the related inv...
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 belongs to the field of computer vision, particularly relates to a binocular vision real-time perception and positioning method, system and device for marine product fetching, and aims to solve the problem of tracking failure caused by insufficient perception and positioning precision of marine products. The binocular vision real-time perception and positioning method comprises the steps: binocular vision image pairs are acquired and polar line alignment is carried out; a current system state is acquired, and if the current system state is true, a target detection result of the aligned image pair in the marine product is acquired based on a deep learning algorithm, and a tracker tracking result is obtained by comparing center points of the target detection result according toa left image tracking result and a right image tracking result; if the target detection result is false, the target detection result comprises any preset type of marine product target, the detectionresults of the left image and the right image form a point pair set, and polar line and position matching is carried out, and a tracker tracking result is obtained, and otherwise, image comparison isobtained again; and according to the tracker tracking result and the current system state, the type and three-dimensional coordinates of the marine product is obtained. According to the invention, thesensing and positioning precision and reliability of marine products are improved.
Description
technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a binocular vision real-time perception positioning method, system and device for grasping seafood. Background technique [0002] Among the various applications of autonomous underwater vehicles, seafood fishing is a very challenging task. In seafood fishing tasks, real-time perception and positioning of seafood is an essential part of any fishing system. Obviously, the real-time sensing and positioning system can be divided into two parts: the real-time sensing and positioning of seafood: the sensing part is mainly to detect the position of seafood in the aircraft's field of vision; the positioning needs to obtain the three-dimensional coordinates of seafood relative to the aircraft. Additionally, since seafood farms are typically located close to well-lit shorelines, vision systems can serve as the primary means of underwater perception in detection and capture syste...
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): G06T7/73G06T7/277G06T7/33G06K9/00
CPCG06T7/74G06T7/277G06T7/337G06T2207/10016G06V20/10
Inventor 王睿崔少伟王宇张天栋王硕
Owner INST OF AUTOMATION CHINESE ACAD OF SCI