Video dehazing method based on rolling temporal particle swarm optimization
A technology of particle swarm optimization and rolling time domain, which is applied in image enhancement, image analysis, instruments, etc., can solve the problem that the defogging method cannot achieve the best effect, achieve the best defogging effect and ensure real-time effect
Active Publication Date: 2021-10-15
ZHEJIANG UNIV OF TECH
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Existing video surveillance defogging is often applied to fixed scenes, and it is easy to find fixed reference objects and fixed overall atmospheric light parameter positions in the scene; while in videos shot by drones, due to the continuous movement of the shooting location and the scene, the environmental parameters It is also constantly changing. In the past, the dehazing method for a single image of a fixed scene could not achieve the best effect.
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] The present invention will be further described below through specific embodiments in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited thereto.
[0047] The implementation uses a hybrid rolling time-domain optimization based on cycle and event-driven (such as figure 1 shown): when the cycle-based rolling time domain optimization is used, the number of frames between the images is 200 frames; when the event-driven rolling time domain optimization is used, it is necessary to meet the scene changes and the last optimized image frame number at the same time Two conditions with an interval of 25. In the process of particle swarm optimization: the number of populations is n=3, and the number of iterations is m=4. When adjusting the brightness, the adjustment coefficient k=7.
[0048] Figure 2 shows the dehazing of aerial video. Figure 2(a)-Figure 2(h) The middle left image is the image to be dehazed, and the right ...
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 present invention is a video defogging method based on rolling time-domain particle swarm optimization, including: 1. In order to construct a comprehensive index with an extreme value, so as to be used to evaluate the image with the best processing effect, the comprehensive membership method is combined with effective details The three features of intensity, structural information and chromaticity information entropy are used to comprehensively evaluate the defogging effect. 2. Use the particle swarm optimization algorithm to obtain the dehazing parameter corresponding to the maximum value of the image evaluation index, which is the current best dehazing parameter. 3. Based on periodic and event-driven, the dehazing parameters are optimized in the hybrid rolling time domain, so that the optimal value of the dehazing parameters can be adaptively adjusted as the scene or environment changes. 4. Using nonlinear superposition method to adjust the brightness of the image after defogging. While ensuring the real-time defogging of the video, the present invention can adaptively optimize the defogging parameters according to the change of the scene or the environment, so as to achieve the best defogging effect.
Description
(1) Technical field [0001] The invention relates to a video dehazing method for rolling optimization of parameters. (2) Background technology [0002] In the 1970s, rolling time domain optimization (Receding Horizon Optimization) predictive control, also known as model predictive control, appeared. The control method takes rolling window technology as the main idea, adopts a hybrid scheduling strategy based on cycle and event drive, and is mainly used in industrial process control and dynamic scheduling of public systems. [0003] Compared with image dehazing, video dehazing puts forward higher requirements for the real-time performance of dehazing: in video dehazing, in order to maintain the frame rate of the video, the processing speed of the video image needs to be controlled within 40ms. Existing video surveillance defogging is often applied to fixed scenes, and it is easy to find fixed reference objects in the scene and fixed positions of the overall atmospheric light ...
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 Patents(China)
IPC IPC(8): G06T5/00G06N3/00
CPCG06N3/006G06T2207/10016G06T5/90G06T5/73
Inventor 张霓曾乐襄何熊熊
Owner ZHEJIANG UNIV OF TECH