Research on Image Detection Algorithm Based on Improved Retinanet

2020 ◽  
Author(s):  
Wenxian Zeng ◽  
Shuqing Zhang ◽  
Yue Zhang ◽  
Yue Ma
Keyword(s):  
Detection Algorithm ◽  
Image Detection

Fuzzy Penetration Control for TIG Weld Based on Wavelet-Fractal

2013 ◽  
Vol 722 ◽  
pp. 545-549
Author(s):  
Li Qin Zhang ◽  
Li Ling Zhang ◽  
Le Hui Huang
Keyword(s):  
Closed Loop ◽  
Welding Process ◽  
Detection Algorithm ◽  
Image Feature ◽  
Fuzzy Pid ◽  
Image Detection ◽  
Controlling System ◽  
Welding Automation ◽  
Welding Image ◽  
Poor Stability

Image detection was the important step of Welding automation. In view of the welding image feature of strong noise and poor stability, conventional detect method can not get the clear welding process image, so a fuzzy detection algorithm of welding image based on wavelet and fractal denoising was presented. The fuzzy detection algorithm is used to process welding image and extract molten-pools edge; and then fuzzy PID controlling theory are combined to form a whole image processing and closed-loop penetration controlling system. The experimental results indicated that the controlling system has the good anti-interference ability in welding process and therefore ensure the stabilization of welding formation quality.

scholarly journals Image target detection algorithm compression and pruning based on neural network

2021 ◽  
Vol 18 (2) ◽  
pp. 499-516
Author(s):  
Yan Sun ◽  
Zheping Yan
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Target Detection ◽  
Network Model ◽  
Detection Algorithm ◽  
Image Feature ◽  
Propagation Mode ◽  
Learning Technology ◽  
Image Detection ◽  
Detection Algorithms

The main purpose of target detection is to identify and locate targets from still images or video sequences. It is one of the key tasks in the field of computer vision. With the continuous breakthrough of deep machine learning technology, especially the convolutional neural network model shows strong Ability to extract image feature in the field of digital image processing. Although the model research of target detection based on convolutional neural network is developing rapidly, but there are still some problems in practical applications. For example, a large number of parameters requires high storage and computational costs in detected model. Therefore, this paper optimizes and compresses some algorithms by using early image detection algorithms and image detection algorithms based on convolutional neural networks. After training and learning, there will appear forward propagation mode in the application of CNN network model, providing the model for image feature extraction, integration processing and feature mapping. The use of back propagation makes the CNN network model have the ability to optimize learning and compressed algorithm. Then research discuss the Faster-RCNN algorithm and the YOLO algorithm. Aiming at the problem of the candidate frame is not significant which extracted in the Faster- RCNN algorithm, a target detection model based on the Significant area recommendation network is proposed. The weight of the feature map is calculated by the model, which enhances the saliency of the feature and reduces the background interference. Experiments show that the image detection algorithm based on compressed neural network image has certain feasibility.

X-ray Security Inspection Image Detection Algorithm Based on Improved YOLOv4

2021 ◽  
Author(s):  
Cheng Zhou ◽  
Hui Xu ◽  
Bicai Yi ◽  
Weichao Yu ◽  
Chenwei Zhao
Keyword(s):  
Detection Algorithm ◽  
Image Detection ◽  
X Ray ◽  
Security Inspection

Study on Image Detection Method of Navigation Route for Cotton Harvester

2012 ◽  
Vol 246-247 ◽  
pp. 219-224 ◽  
Author(s):  
Jing Bin Li ◽  
Bing Qi Chen ◽  
Yang Liu ◽  
Tao Zha
Keyword(s):  
Hough Transform ◽  
Processing Time ◽  
Detection Method ◽  
Point Group ◽  
Color Difference ◽  
Detection Algorithm ◽  
Boundary Line ◽  
Working Process ◽  
Image Detection ◽  
Candidate Point

This paper presents an image detection algorithm for navigation route of cotton harvester. Two cameras were respectively installed on the leftmost and rightmost picker unit, and images were captured during working process respectively. Firstly, the color characteristics among harvested field, un-harvested field, outside-field and the end of field were analyzed, then the target features of different fields was extracted using the color difference 3B-R-G. Secondly, candidate point group was determined by looking for the critical point of peak from the lowest trough point to un-harvested field and associating with the detection result of the anterior frame. Lastly, navigation line was obtained by using passing a Known Point Hough Transform (PKPHT). Results show that the navigation line detected using this algorithm can fit the boundary line and the edge of field accurately, the average processing time is56.10ms/f, and the algorithm can meet the actual production needs of cotton harvester.

scholarly journals Reliable Template Matching for Image Detection in Vision Sensor Systems

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8176
Author(s):  
Youngmo Han
Keyword(s):  
Template Matching ◽  
Closed Form Solution ◽  
Detection Algorithm ◽  
Ease Of Use ◽  
Sensor System ◽  
Size Difference ◽  
Vision Sensor ◽  
Projection Model ◽  
Image Detection ◽  
Additional Information

Template matching is a simple image detection algorithm that can easily detect different types of objects just by changing the template without tedious training procedures. Despite these advantages, template matching is not currently widely used. This is because traditional template matching is not very reliable for images that differ from the template. The reliability of template matching can be improved by using additional information (depths for the template) available from the vision sensor system. Methods of obtaining the depth of a template using stereo vision or a few (two or more) template images or a short template video via mono vision are well known in the vision literature and have been commercialized. In this strategy, this paper proposes a template matching vision sensor system that can easily detect various types of objects without prior training. To this end, by using the additional information provided by the vision sensor system, we study a method to increase the reliability of template matching, even when there is a difference in the 3D direction and size between the template and the image. Template images obtained through the vision sensor provide a depth template. Using this depth template, it is possible to predict the change of the image according to the difference in the 3D direction and the size of the object. Using the predicted changes in these images, the template is calibrated close to the given image, and then template matching is performed. For ease of use, the algorithm is proposed as a closed form solution that avoids tedious recursion or training processes. For wider application and more accurate results, the proposed method considers the 3D direction and size difference in the perspective projection model and the general 3D rotation model.

Sign in / Sign up

Export Citation Format

Share Document