Journals >Opto-Electronic Engineering
Contents
2020
Volume: 47 Issue 1
11 Article(s)
Export citation format
Research Articles
Research on target tracking based on convolutional networks
Zhao Chunmei, Chen Zhongbi, and Zhang Jianlin
In this paper, aiming at the application of target tracking, an improved convolutional network Siamese-MF (multi-feature Siamese networks) based on Siamese-FC (fully-convolutional Siamese networks) is proposed to fur-ther improve the tracking speed and accuracy to meet the requirements of target tracking in engineeringIn this paper, aiming at the application of target tracking, an improved convolutional network Siamese-MF (multi-feature Siamese networks) based on Siamese-FC (fully-convolutional Siamese networks) is proposed to fur-ther improve the tracking speed and accuracy to meet the requirements of target tracking in engineering applications. For tracking networks, considering the trade-off between speed and accuracy, reducing computational complexity and increasing the receptive field of convolution feature are the directions to improve the speed and accuracy of tracking networks. There are two main points to improve the structure of convolution network: 1) introducing feature fusion to enrich features; 2) introducing dilated convolution to reduce the amount of computation and enhance the field of perception. Siamese-MF algorithm achieves real-time and accurate tracking of targets in complex scenes. The average speed of testing on OTB of public data sets reaches 76 f/s, the average value of overlap reaches 0.44, and the average value of accuracy reaches 0.61. The real-time, accuracy and stability are improved to meet the requirement in real-time target tracking application..
Opto-Electronic Engineering
- Publication Date: Jan. 01, 1900
- Vol. 47, Issue 1, 180668 (2020)
Joint energy active contour CT image segmentation method based on super-pixel
Liu Xia, Gan Quan, Liu Xiao, and Wang Bo
In this paper, an active contour segmentation method for organs CT images based on super-pixel and convolutional neural network is proposed to solve the sensitive problem of the initial contour of the segmentation method of the CT image. The method firstly super-pixels the CT image based on super-pixel segmentation andIn this paper, an active contour segmentation method for organs CT images based on super-pixel and convolutional neural network is proposed to solve the sensitive problem of the initial contour of the segmentation method of the CT image. The method firstly super-pixels the CT image based on super-pixel segmentation and de-termines the edge super-pixels by the super-pixel classification through a convolutional neural network. Afterwards, the seed points of the edge super-pixels are extracted to form the initial contour. Finally, based on the extracted initial contour, the human organ segmentation is realized by solving the minimum value of the integrated energy function proposed in this paper. The results in this paper show that the average Dice coefficient is improved by 5% compared with the advanced U-Net method, providing a theoretical basis and a new solution for the diagnosis of clinical CT image lesions..
Opto-Electronic Engineering
- Publication Date: Jan. 01, 1900
- Vol. 47, Issue 1, 190104 (2020)
Rotating invariant face detection via cascaded networks and pyramidal optical flows
Sun Rui, Kan Junsong, Wu Liuwei, and Wang Peng
In the unconstrained open-space, face detection is still a challenging task due to the facial posture changes, complex background environment, and motion blur. The rotation-invariant algorithm based on cascaded network and pyramid optical flow is proposed. Firstly, the cascading progressive convolutional neural networkIn the unconstrained open-space, face detection is still a challenging task due to the facial posture changes, complex background environment, and motion blur. The rotation-invariant algorithm based on cascaded network and pyramid optical flow is proposed. Firstly, the cascading progressive convolutional neural network is adopted to locate the face position and facial landmark of the previous frame in the video stream. Secondly, the in-dependent facial landmark detection network is used to reposition the current frame, and the optical flow mapping displacement of the facial landmark between the two frames is calculated afterwards. Finally, the detected face is corrected by the mapping relationship between the optical flow displacement of the facial landmark and the bounding box, thereby completing the rotation-invariant face detection. The experiment was tested on the FDDB public data-sets, which proved that the method is more accurate. Moreover, the dynamic test on the Boston head tracking da-tabase proves that the face detection algorithm can effectively solve the problem of rotation-invariant face detection. Compared with other detection algorithms, the detection speed of the proposed algorithm has a great advantage, and the window jitter problem in the video is well solved..
Opto-Electronic Engineering
- Publication Date: Jan. 01, 1900
- Vol. 47, Issue 1, 190135 (2020)
Multi-candidate association online multi-target
tracking based on R-FCN framework
E Gui, and Wang Yongxiong
Online multi-target tracking is an important prerequisite for real-time video sequence analysis. Because of low reliability in target detection, high tracking loss rate and unsmooth trajectory in online multi-target tracking, an online multi-target tracking model based on R-FCN (region based fully convolutional networkOnline multi-target tracking is an important prerequisite for real-time video sequence analysis. Because of low reliability in target detection, high tracking loss rate and unsmooth trajectory in online multi-target tracking, an online multi-target tracking model based on R-FCN (region based fully convolutional networks) network framework is proposed. Firstly, the target evaluation function based on R-FCN network framework is used to select more reliable candidates in the next frame between KF and detection results. Second, the Siamese network is used to perform similarity measurement based on appearance features to complete the match between candidates and tracks. Finally, the tracking trajectory is optimized by the RANSAC (random sample consensus) algorithm. In crowded and partially occluded complex scenes, the proposed algorithm has higher target recognition ability, greatly reduces the phenomenon of missed detection and false detection, and the tracking track is more continuous and smooth. The experimental results show that under the same conditions, compared with the existing methods, the performance indicators of the proposed method, such as target tracking accuracy (MOTA), number of lost trajectories (ML) and number of false positives (FN), have been greatly improved..
Opto-Electronic Engineering
- Publication Date: Jan. 01, 1900
- Vol. 47, Issue 1, 190136 (2020)
An open-pit mine roadway obstacle warning method integrating the object detection and distance threshold model
Lu Caiwu, Qi Fan, and Ruan Shunling
In order to solve the problem that the current driving warning method cannot adapt to the unstructured road in open-pit mine, this paper proposes an early warning method that integrates target detection and obstacle istance threshold. Firstly, the original Mask R-CNN detection framework was improved according to the chIn order to solve the problem that the current driving warning method cannot adapt to the unstructured road in open-pit mine, this paper proposes an early warning method that integrates target detection and obstacle istance threshold. Firstly, the original Mask R-CNN detection framework was improved according to the characteristics of open-pit mine obstacles, and dilated convolution was introduced into the framework network to expand the receptive field range without reducing the feature map to ensure the detection accuracy of larger targets. Then, a linear distance factor was constructed based on the target detection results to represent the depth information of obstacles in the input image, and an SVM warning model was established. Finally, in order to ensure the generalization ability of the warning model, transfer learning method was adopted to carry out pre-training of the network in COCO data set, and both the C5 stage and detection layer were trained in the data collected in the field. The experimental results show that the accuracy and recall of the proposed method reach 98.47% and 97.56% in the field data detection, respectively, and the manually designed linear distance factor has a good adaptability to the SVM warning model..
Opto-Electronic Engineering
- Publication Date: Jan. 01, 1900
- Vol. 47, Issue 1, 190161 (2020)
Vessel enhancement of endoscopic image based on multi-color space
Wang Qiang, Tao Pei, Yuan Bo, and Wang Liqiang
In order to improve the contrast between the blood vessels and tissues of the images obtained by medical electronic endoscopes, a vessel enhancement method of non-linear contrast stretching in multi-color space is proposed according to the characteristics of endoscopic vascular images. Firstly, in RGB color space, streIn order to improve the contrast between the blood vessels and tissues of the images obtained by medical electronic endoscopes, a vessel enhancement method of non-linear contrast stretching in multi-color space is proposed according to the characteristics of endoscopic vascular images. Firstly, in RGB color space, stretching contrast adaptively of the green (G) component by using the nonlinear mapping function. Secondly, adjusting the gray value of the two components of red (R) and blue (B) according to the stretching result of the G component. Thirdly, converting the image to HSV color space, and stretching contrast adaptively of the saturation (S) component of the
image. Finally, converting the image back to RGB color space, and the purpose of vessel enhancement is achieved. In this paper, the proposed algorithm is used to process several electronic endoscopic images with different contrast and brightness. The results show that the algorithm has better enhancement effect on small blood vessels which are not obvious in original features. Comparing to other enhancement methods, the detail variance (DV) of the enhanced image is significantly great. The algorithm is embedded in a resolution of 1280×800 endoscopic software, 26 frames can be processed per second. .
Opto-Electronic Engineering
- Publication Date: Jan. 01, 1900
- Vol. 47, Issue 1, 190268 (2020)
Anti-occlusion and re-tracking of real-time moving target based on kernelized correlation filter
Tang Xuemeng, Chen Zhiguo, and Fu Yi
The correlation filtering algorithm determines the target position by the similarity between the template and the detection target. Since the related filtering concept is used for target tracking, it has been widely concerned, and the proposal of the kernelized correlation filter is to push this concept to a new heightThe correlation filtering algorithm determines the target position by the similarity between the template and the detection target. Since the related filtering concept is used for target tracking, it has been widely concerned, and the proposal of the kernelized correlation filter is to push this concept to a new height. The kernelized correlation filter has become a research hotspot with its high speed, high precision and high robustness. However, the kernelized correlation filter has serious defects in anti-blocking performance. In this paper, the algorithm for the anti-occlusion performance of kernelized correlation filter is improved. An improved KCF algorithm based on Sobel edge binary mode algorithm is proposed. The Sobel edge binary mode algorithm is used to weight the fusion target feature. The target's peak response intensity sidelobe value is more than the detection target is lost. Finally, the Kalman algorithm is used as the target occlusion strategy. The results show that the proposed method not only has better robustness against occlusion, but also satisfy the real-time requirements and can accurately re-tracks the target..
Opto-Electronic Engineering
- Publication Date: Jan. 01, 1900
- Vol. 47, Issue 1, 190279 (2020)
Multi-angle key point detection of face based on deep learning detector
Zhao Xingwen, Hang Lijun, Gong Enlai, Ye Feng, and Ding Mingxu
In order to meet the speed and accuracy requirements of face key point detection (face alignment) in ap-plication scenarios, firstly, cascaded prediction is carried out on the basis of SSD (single shot multibox detector),which combines more uniformly distributed feature layers to form MR-SSD (more robust SSD), a deep lIn order to meet the speed and accuracy requirements of face key point detection (face alignment) in ap-plication scenarios, firstly, cascaded prediction is carried out on the basis of SSD (single shot multibox detector),which combines more uniformly distributed feature layers to form MR-SSD (more robust SSD), a deep learning de-tector with more robust response to multi-scale faces. Secondly, based on the cascade shape regression method oflocal binary feature (LBF), a multi-angle initialization algorithm based on the difference between the facial pixels isproposed. Five groups of feature points in the 90 degree inclination range of positive and negative face are initializedto achieve excellent fitting effect for inclined face under multi angles. The mean square deviation of each group offeature points after regression is calculated and the maximum corresponding shape is used as the final regressionshape. The optimal architecture proposed in this paper can obtain robust face bounding box and face alignmentschemes against multi-angle tilt in real time..
Opto-Electronic Engineering
- Publication Date: Jan. 01, 1900
- Vol. 47, Issue 1, 190299 (2020)
Research on defect inspection method of pipeline robot based on adaptive image enhancement
Li Ping, Liang Dan, Liang Dongtai, Wu Xiaocheng, and Chen Xing
In view of the problem about uneven image acquisition and inaccurate edge extraction in pipeline detection process, a pipeline robot defect inspection method based on adaptive image enhancement is proposed. Firstly, a single-scale Retinex adaptive image enhancement algorithm is designed, which uses the guided filter toIn view of the problem about uneven image acquisition and inaccurate edge extraction in pipeline detection process, a pipeline robot defect inspection method based on adaptive image enhancement is proposed. Firstly, a single-scale Retinex adaptive image enhancement algorithm is designed, which uses the guided filter to estimate the illumination component of the Value component of the image, and gets the illumination equilibrium image by adaptive Gamma correction, so as to realize the image enhancement. Then, the traditional Canny edge detection method is improved, using bilateral filtering to smooth the image. Besides, the defect images are segmented by the iterative threshold method, and the edge connection is carried out according to the edge pixel similarity. Therefore, the defect contour of the pipe-wall is extracted effectively. Thirdly, a pipeline robot defect detection system based on adaptive image enhancement is built, and a crawler car equipped with the pan-tilt-zoom camera conducts all-round visual inspection of the defects in the pipeline inner wall. The experimental results show that the detection method in this paper can adaptively correct the image brightness, and the uneven brightness of the image is significantly improved. Compared with the sub-optimal algorithm, the information entropy of the image is increased by 2.4%, the average gradient of the image is increased by 2.3%, and the peak signal to noise ratio is increased by 4.4%, and the pipeline defect edges are extracted effectively with the detection accuracy up to 97%..
Opto-Electronic Engineering
- Publication Date: Jan. 01, 1900
- Vol. 47, Issue 1, 190304 (2020)
Performance study of multi-hop coherent OFDM FSO system over M distribution model
Wu Hao, and Wang Yi
The performance of multi-hop coherent orthogonal frequency division multiplexing (OFDM) free space optical (FSO) system is studied by using quadrature phase shift keying (QPSK) modulation in this paper. A genera-lized model called M distribution is selected, which is suitable for all categories of turbulence ranging frThe performance of multi-hop coherent orthogonal frequency division multiplexing (OFDM) free space optical (FSO) system is studied by using quadrature phase shift keying (QPSK) modulation in this paper. A genera-lized model called M distribution is selected, which is suitable for all categories of turbulence ranging from weak to strong and characterizes other existing statistical models of atmospheric turbulence induced fading as its special case. The system uses decode and forward (DF) relay protocol between the transmitter and receiver of the relay auxiliary link. Considering the joint attenuation effects of atmospheric turbulence, path loss and pointing error on the atmospheric channel fading model, we derive the Meijer G closed-form expressions of outage probability and symbol error rate (SER). Furthermore, the effects of key factors, such as relay link length, the number of relay nodes and subcarriers on the outage and SER performance of OFDM FSO system are analyzed through simulations. This work lays a theoretical foundation for the practical application of the relay system..
Opto-Electronic Engineering
- Publication Date: Jan. 01, 1900
- Vol. 47, Issue 1, 190337 (2020)
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20