Application of a Model that Combines the YOLOv3 Object Detection Algorithm and Canny Edge Detection Algorithm to Detect Highway Accidents

Rheumatoid arthritis (RA) is a long lasting autoimmune disorder that affects the multiple joints of human body. The aim and objective of the study was i) to implement the automated segmentation of knee x-ray image and thermal image using fuzzy c means and canny edge detection algorithm. ii) To compare both the imaging modalities by means of feature extraction and correlate with the biochemical method as standard. Fifteen subjects with RA in knee region and 15 healthy controls were included in this study. The segmentation of thermal images was performed using fuzzy c-means algorithm and x-ray segmentation was implemented using canny edge detection algorithm. The skin surface temperature weremeasured in the thermal image of knee regionin both RA and control subjects. The features wereextracted from the segmented region of the knee x-ray image. The automated segmentation implemented in thermal imaging provided better results compared to x-ray image segmentation process. The thermal imaging feature and x-ray imaging features correlated significantly with the standard parameters.

In stereo vision, disparity map after stereo matching using projection model can get the depth information and 3D information of the original image. In order to improve the accuracy and speed of stereo matching, improving the quality of disparity map becomes the core problem of stereo matching. Firstly, the paper extracted edge information of binocular images using Canny, Scharr and Sobel edge detection algorithm. On this basis, the paper use SGBM algorithm(Semi-global block Matching) and DP algorithm(Dynamic Programming)and CSCA algorithm(Cross-scale Cost Aggregation) respectively calculated the disparity map and its error rate. After analysis, the combination of Canny detection algorithm and CSCA algorithm can eliminate a large number of number of irrelevant information and reduce the amount of data processing. The real scene image is selected to validate the method .Based on the above research results, the method improved the quality of disparity map.

Image edge detection significantly preserves the important structural properties in an image, while reducing the amount of data and filters out useless information. Since edge detection is in the forefront of image processing for object detection, it is crucial to have a good understanding of edge detection algorithms. This paper introduces the Canny edge detection algorithm and the implementation of the Canny edge-detection algorithm on an FPGA. Custom implementation in FPGAs, using a combination of hardware and software co-design, allows real-time processing, providing a good trade-off between performance and flexibility. The results show that FPGAs are good alternatives, which can be used to off-load these computationally-intensive and repetitive functions as co-processors and the capability of supporting canny edge detection for real-time image processing.

The Canny edge detection algorithm contains a number of adjustable parameters, which can affect the computation time and effectiveness of the algorithm. To overcome the shortages, this paper proposes a new way to determine the adjustable parameters and constructs a modified Canny edge detection algorithm. In the algorithm, an image is firstly smoothed by an adaptive filter that is selected based on the properties of the image, instead of a fixed sized Gaussian filter, and then, the high and low thresholds for the gradient magnitude image are determined based on maximum cross-entropy between inter-classes and Bayesian judgment theory, without any manual operation; finally, if it needs, the object closing procedure is carried out. To test and evaluate the algorithm, a number of different images are tested and analysed, and the test results are discussed. The experiments show that the studied algorithm can achieve the better edge detection results in most of the cases, and it is also useful for object boundary closing as a pre-segmentation step.

Integration of image processing in order to detect red blood cells (RBCs) in human urine enables technology to reduce medical technician’s manual counting time and error factor. The general objective of this study was to detect and count the red blood cells in human urine using Canny Edge Detection (CED) and Circle Hough Transform (CHT) algorithms. CED is an edge detection algorithm used in order to identify a great variety of edges in an image. CHT is one of the features of the Hough Transform. Specifically, CHT is used in order to detect circular objects. The basis of the CHT operation will be dependent on the circular edges detected by the CED. In order to identify a specific circle size, the minimum and maximum radius must be set. Particularly, to differentiate the RBCs from other cells such as white blood cells. For this study, the minimum radius was 4 pixels while the maximum was 6. Compared to the manual counting of a medical technician, the automated counting of the device produced a percent error of 9.561% and an average counting time of 0.4561 seconds per sample.

In order to detect obstacles on the runway without the ground obstacle detection system, a vision-based autonomous detection scheme is proposed in this paper. An algorithm based on adaptive singular value decomposition and reconstruction (AS VDR) is adopted to identify and segment the runway region accurately by combining Canny operator edge detection algorithm and Hough line detection algorithm. The useful information about the runway and the obstacle which is not on the same plane as the runway can be obtained by an algorithm based on optical flow field. A method based on mixed Gauss background model is used to evaluate the information of the optical flow field in the runway area, and then calculate the confidence level of the obstacle. Through these algorithms, it can put out the final decision of whether to land or not. The experimental results show that the difference of confidence level curves between the runway with obstacles and that without obstacles is large enough to determine whether there are obstacles. The accurate scaled model simulation results show that the scheme is feasible and accurate.

Automatic classification of apples is an important application of machine vision technology in agricultural product detection. In this paper, we study apple grading method based on features of color and defect. First, the captured RGB-based apple images are transformed into HIS model. Then, the segmentation between fruit and background is realized via the Oust algorithm for the H values of the image, and the color feature is extracted by the appropriate range of H values. In addition, the Canny edge detection algorithm with hysteresis threshold is employed to extract the edge information of defect area from I values of fruit image, then the defect area is segmented by morphological operation. Finally, serving as input, the characteristic quantities of apple color and surface defect are sent into the SVM model based on particle swarm optimization. The experiment results indicate that accuracy rate can reach to 91%.

Learned active contours via transformer-based deep convolutional neural network using canny edge detection algorithm

The iris, an annulus region where located in the area between the pupil and sclera, its unique texture almost never changes in whole life. Iris location is to locate the effective region and prevent interference with the invalid region. Iris localization is an important part in the Iris recognition system, accuracy and speed of the positioning directly affects the performance of iris recognition system. On the basis of existing analysis on iris recognition algorithms, dividing the positioning process into two steps: the rough positioning and the precise positioning. In the first step, based on gray window, which can reduce the specifically searching range and can avoid the eyelash, eyelids and the disturbance of external spotlight source effectively, etc., we introduce a new method that estimates coarse positioning of pupil center. In the step of fine positioning, based on Canny edge detection algorithm and the Hough transform, we introduce an improved algorithm. In the process of Edge extraction, utilizing the feature between internal and outer edges and the Hough transform, we adjust the size of extracted image block, a small image would be fixed the size due to the prior experimental results. Experimental results show that the localization algorithm ensure the accuracy of iris localization while enhancing the localization speed. Effectively overcome the serious influence of eyelids and eyelashes. In conclusion, The Improved Iris Location Algorithm is feasible.

The compound nested control method of PID control and fuzzy control is used to control the walking position and speed of the bridge crane, and image processing technology is applied to detect the critical position during rotor hoisting. The system simulation is carried out using Matlab/Simulink, and the feasibility of the control method is verified based on the overshoot, response time, and stability indicators with the unit step signal as the excitation. The results show that the time required to reach steady state through fixed parameter PID simulation analysis is 0.237 s, and the overshoot is 3.3%. The time required for steady state using fuzzy PID control is 0.12s, the response speed is better than that of fixed parameter PID control, and the system has no overshoot. The image of the stator captured by the camera is processed by OpenCV. Firstly, the image is grayed and the Gaussian filtering is used to remove the image noise. Then, the stator edge contour is detected based on the Canny edge detection algorithm. The test shows that OpenCV can accurately identify the edge of the stator and extract the central coordinates of the stator image, which assists the bridge crane in accurate positioning.

The purpose of this study was to investigate the ability of quantitative ultrasound (US) using edge detection analysis to assess patients with Duchenne muscular dystrophy (DMD). After Institutional Review Board approval, US examinations with fixed technical parameters were performed unilaterally in 6 muscles (biceps, deltoid, wrist flexors, quadriceps, medial gastrocnemius, and tibialis anterior) in 19 boys with DMD and 21 age-matched control participants. The muscles of interest were outlined by a tracing tool, and the upper third of the muscle was used for analysis. Edge detection values for each muscle were quantified by the Canny edge detection algorithm and then normalized to the number of edge pixels in the muscle region. The edge detection values were extracted at multiple sensitivity thresholds (0.01-0.99) to determine the optimal threshold for distinguishing DMD from normal. Area under the receiver operating curve values were generated for each muscle and averaged across the 6 muscles. The average age in the DMD group was 8.8 years (range, 3.0-14.3 years), and the average age in the control group was 8.7 years (range, 3.4-13.5 years). For edge detection, a Canny threshold of 0.05 provided the best discrimination between DMD and normal (area under the curve, 0.96; 95% confidence interval, 0.84-1.00). According to a Mann-Whitney test, edge detection values were significantly different between DMD and controls (P < .0001). Quantitative US imaging using edge detection can distinguish patients with DMD from healthy controls at low Canny thresholds, at which discrimination of small structures is best. Edge detection by itself or in combination with other tests can potentially serve as a useful biomarker of disease progression and effectiveness of therapy in muscle disorders.

In this paper, image smoothening, gradient magnitude, hystersis used in Canny edge detection algorithm is presented. The new algorithm used has a low-complexity 8-bin non-uniform gradient magnitude histogram to compute block-based hysteresis thresholds that are used by the Canny edge detector. This also achieves less memory requirements, decreased latency and increased throughput with no loss in edge detection. Furthermore, the hardware architecture of the proposed algorithm is presented in this paper and the architecture is synthesized on the Xilinx Virtex 5 FPGA. The design development is done in VHDL and simulated results are obtained using modelsim 6.3 with Xilinx 12.2.

Accurate diagnosis of Alzheimer’s Disease (AD) is of great importance to patient care, especially in the early stage, because it enables patients to take preventive measures before irreversible brain damage occurs. Obviously, if computer-based diagnostic models can make better predictions than doctors, the future of health care will change dramatically from the current system. Based on magnetic resonance imaging (MRI), this paper realizes a classification algorithm to distinguish AD patients from normal people. OASIS Brain Imaging Data Set is an open source online data set, which is a coronal bitmap of the human brain. Canny edge detection algorithm is used to extract image information, and K-Means and convolution neural network (CNN) are used to train the data set. The results show that the recognition accuracy of the training set is 99%, and 26% higher than that of the K-Means algorithm, which can be effectively used in the early diagnosis of Alzheimer’s disease.

Grey-scale multiresolution cross-correlation, combined with Canny edge detection algorithms, has been proposed and investigated for relatively simple and efficient coin recognition and matching algorithm. First experiments and investigations of the proposed solution show promising results. Also an overview of the alternative or complimentary image matching by support vector machines algorithm has been given in the paper. Finally, ideas for further improvement of the efficiency of the proposed solution are discussed.

The necessity of distinguishing elements of the urban infrastructure on the optoelectronic images of remote sensing of the Earth is substantiated. Known methods for the selection of contours and their main disadvantages are analyzed. A method for isolating the contours of urban infrastructure objects on optoelectronic images of remote sensing of the Earth is proposed. The method includes two stages. The first stage is the selection of contours by the Canny edge detection algorithm. The second stage is the selection of geometric primitives using the Hough transform. The color image of the onboard Earth remote sensing system was processed. The results of the method at each intermediate stage are given. The assessment of the quality of the selection of the contours of urban infrastructure in the image carried out by visual means.