scholarly journals Falling motion detection algorithm based on deep learning

2021 ◽  
Author(s):  
Na Zhu ◽  
Guangzhe Zhao ◽  
Xiaolong Zhang ◽  
Zhexue Jin
Keyword(s):  
Deep Learning ◽  
Motion Detection ◽  
Detection Algorithm

scholarly journals Deep Learning-Driven Gaussian Modeling and Improved Motion Detection Algorithm of the Three-Frame Difference Method

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Dingchao Zheng ◽  
Yangzhi Zhang ◽  
Zhijian Xiao
Keyword(s):  
Deep Learning ◽  
Motion Detection ◽  
Adaptive Learning ◽  
Difference Method ◽  
Gaussian Model ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Frame Difference ◽  
Gaussian Modeling ◽  
Difference Calculation

To enhance the effect of motion detection, a Gaussian modeling algorithm is proposed to fix holes and breaks caused by the conventional frame difference method. The proposed algorithm uses an improved three-frame difference method. A three-frame image sequence with one frame interval is selected for pairwise difference calculation. The logical “OR” operation is used to achieve fast motion detection and to reduce voids and fractures. The Gaussian algorithm establishes an adaptive learning model to make the size and contour of the motion detection more accurate. The motion extracted by the improved three-frame difference method and Gaussian model is logically summed to obtain the final motion foreground picture. Moreover, a moving target detection method, based on the U-Net deep learning network, is proposed to reduce the dependency of deep learning on the number of training datasets. It helps the algorithm to train models on small datasets. Next, it calculates the ratio of the number of positive and negative samples in the dataset and uses the reciprocal of the ratio as the sample weight to deal with the imbalance of positive and negative samples. Finally, a threshold is set to predict the results for obtaining the moving object detection accuracy. Experimental results show that the algorithm can suppress the generation and rupture of holes and reduce the noise. Also, it can quickly and accurately detect movement to meet the design requirements.

scholarly journals Influence of patient motion on quantitative accuracy in cardiac 15O-water positron emission tomography

2021 ◽  
Author(s):  
Jonny Nordström ◽  
Hendrik J. Harms ◽  
Tanja Kero ◽  
Jens Sörensen ◽  
Mark Lubberink
Keyword(s):  
Motion Detection ◽  
Detection Algorithm ◽  
Clinical Effects ◽  
Average Deviation ◽  
Patient Motion ◽  
Motion Data ◽  
Positron Emission ◽  
Quantitative Accuracy ◽  
Pet Ct ◽  
Using Data

Abstract Background Patient motion is a common problem during cardiac PET. The purpose of the present study was to investigate to what extent motions influence the quantitative accuracy of cardiac 15O-water PET/CT and to develop a method for automated motion detection. Method Frequency and magnitude of motion was assessed visually using data from 50 clinical 15O-water PET/CT scans. Simulations of 4 types of motions with amplitude of 5 to 20 mm were performed based on data from 10 scans. An automated motion detection algorithm was evaluated on clinical and simulated motion data. MBF and PTF of all simulated scans were compared to the original scan used as reference. Results Patient motion was detected in 68% of clinical cases by visual inspection. All observed motions were small with amplitudes less than half the LV wall thickness. A clear pattern of motion influence was seen in the simulations with a decrease of myocardial blood flow (MBF) in the region of myocardium to where the motion was directed. The perfusable tissue fraction (PTF) trended in the opposite direction. Global absolute average deviation of MBF was 3.1% ± 1.8% and 7.3% ± 6.3% for motions with maximum amplitudes of 5 and 20 mm, respectively. Automated motion detection showed a sensitivity of 90% for simulated motions ≥ 10 mm but struggled with the smaller (≤ 5 mm) simulated (sensitivity 45%) and clinical motions (accuracy 48%). Conclusion Patient motion can impair the quantitative accuracy of MBF. However, at typically occurring levels of patient motion, effects are similar to or only slightly larger than inter-observer variability, and downstream clinical effects are likely negligible.

scholarly journals High-Speed Lightweight Ship Detection Algorithm Based on YOLO-V4 for Three-Channels RGB SAR Image

2021 ◽  
Vol 13 (10) ◽  
pp. 1909
Author(s):  
Jiahuan Jiang ◽  
Xiongjun Fu ◽  
Rui Qin ◽  
Xiaoyan Wang ◽  
Zhifeng Ma
Keyword(s):  
Deep Learning ◽  
Gpu Computing ◽  
Hot Spot ◽  
Detection Algorithm ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Processing Unit ◽  
Sar Image ◽  
Marine Monitoring ◽  
Ship Detection

Synthetic Aperture Radar (SAR) has become one of the important technical means of marine monitoring in the field of remote sensing due to its all-day, all-weather advantage. National territorial waters to achieve ship monitoring is conducive to national maritime law enforcement, implementation of maritime traffic control, and maintenance of national maritime security, so ship detection has been a hot spot and focus of research. After the development from traditional detection methods to deep learning combined methods, most of the research always based on the evolving Graphics Processing Unit (GPU) computing power to propose more complex and computationally intensive strategies, while in the process of transplanting optical image detection ignored the low signal-to-noise ratio, low resolution, single-channel and other characteristics brought by the SAR image imaging principle. Constantly pursuing detection accuracy while ignoring the detection speed and the ultimate application of the algorithm, almost all algorithms rely on powerful clustered desktop GPUs, which cannot be implemented on the frontline of marine monitoring to cope with the changing realities. To address these issues, this paper proposes a multi-channel fusion SAR image processing method that makes full use of image information and the network’s ability to extract features; it is also based on the latest You Only Look Once version 4 (YOLO-V4) deep learning framework for modeling architecture and training models. The YOLO-V4-light network was tailored for real-time and implementation, significantly reducing the model size, detection time, number of computational parameters, and memory consumption, and refining the network for three-channel images to compensate for the loss of accuracy due to light-weighting. The test experiments were completed entirely on a portable computer and achieved an Average Precision (AP) of 90.37% on the SAR Ship Detection Dataset (SSDD), simplifying the model while ensuring a lead over most existing methods. The YOLO-V4-lightship detection algorithm proposed in this paper has great practical application in maritime safety monitoring and emergency rescue.

scholarly journals Deep Learning-Based Congestion Detection at Urban Intersections

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2052
Author(s):  
Xinghai Yang ◽  
Fengjiao Wang ◽  
Zhiquan Bai ◽  
Feifei Xun ◽  
Yulin Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Optical Flow ◽  
Traffic Congestion ◽  
Detection Algorithm ◽  
Input Image ◽  
Vehicle Speed ◽  
Position Information ◽  
Traffic State ◽  
State Discrimination ◽  
Discrimination Method

In this paper, a deep learning-based traffic state discrimination method is proposed to detect traffic congestion at urban intersections. The detection algorithm includes two parts, global speed detection and a traffic state discrimination algorithm. Firstly, the region of interest (ROI) is selected as the road intersection from the input image of the You Only Look Once (YOLO) v3 object detection algorithm for vehicle target detection. The Lucas-Kanade (LK) optical flow method is employed to calculate the vehicle speed. Then, the corresponding intersection state can be obtained based on the vehicle speed and the discrimination algorithm. The detection of the vehicle takes the position information obtained by YOLOv3 as the input of the LK optical flow algorithm and forms an optical flow vector to complete the vehicle speed detection. Experimental results show that the detection algorithm can detect the vehicle speed and traffic state discrimination method can judge the traffic state accurately, which has a strong anti-interference ability and meets the practical application requirements.

Sign in / Sign up

Export Citation Format

Share Document