Detection of Hands for Hand-Controlled Skyfall Game in Real Time Using CNN

2020 ◽  
Vol 10 (2) ◽  
pp. 15-25
Author(s):  
Neha B. ◽  
Naveen V. ◽  
Angelin Gladston
Keyword(s):  
Real Time ◽  
Detection Methods ◽  
Input Device ◽  
Single Shot ◽  
Hand Detection ◽  
Web Based ◽  
Fast Detection ◽  
Detection And Tracking ◽  
Average Accuracy ◽  
Direct Use

With human-computer interaction technology evolving, direct use of the hand as an input device is of wide attraction. Recently, object detection methods using CNN models have significantly improved the accuracy of hand detection. This paper focuses on creating a hand-controlled web-based skyfall game by building a real time hand detection using CNN-based technique. A CNN network, which uses a MobileNet as the feature extractor along with the single shot detector framework, is used to achieve a robust and fast detection of hand location and tracking. Along with detection and tracking of hand, skyfall game has been designed to play using hand in real time with tensor flow framework. This way of designing the game where hand is used as input to control the paddle of skyfall game improved the player interaction and interest towards playing the game. This model of CNN network used egohands dataset for detecting and tracking the hands in real time and produced an average accuracy of 0.9 for open hands and 0.6 for closed hands which in turn improved player and game interactions.

scholarly journals DWCA-YOLOv5: An Improve Single Shot Detector for Safety Helmet Detection

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Zhang Jin ◽  
Peiqi Qu ◽  
Cheng Sun ◽  
Meng Luo ◽  
Yan Gui ◽  
...  
Keyword(s):  
Information Dissemination ◽  
Detection Efficiency ◽  
A Priori ◽  
Detection Methods ◽  
Single Shot ◽  
Accuracy Rate ◽  
Average Accuracy ◽  
Head Detection ◽  
Matching Degree ◽  
Complex Construction

Aiming at solving the problem that the detection methods used in the existing helmet detection research has low detection efficiency and the cumulative error influences accuracy, a new algorithm for improving YOLOv5 helmet wearing detection is proposed. First of all, we use the K -means++ algorithm to improve the size matching degree of the a priori anchor box; secondly, integrate the Depthwise Coordinate Attention (DWCA) mechanism in the backbone network, so that the network can learn the weight of each channel independently and enhance the information dissemination between features, thereby strengthening the network’s ability to distinguish foreground and background. The experimental results show as follows: in the self-made safety helmet wearing detection dataset, the average accuracy rate reached 95.9%, the average accuracy of the helmet detection reached 96.5%, and the average accuracy of the worker’s head detection reached 95.2%. Making a comparison with the YOLOv5 algorithm, our model has a 3% increase in the average accuracy of helmet detection, which is in line with the accuracy requirements of helmet wearing detection in complex construction scenarios.

scholarly journals Ship Detection Based on YOLOv2 for SAR Imagery

2019 ◽  
Vol 11 (7) ◽  
pp. 786 ◽  
Author(s):  
Yang-Lang Chang ◽  
Amare Anagaw ◽  
Lena Chang ◽  
Yi Wang ◽  
Chih-Yu Hsiao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Real Time ◽  
Experimental Results ◽  
Detection Methods ◽  
Computational Time ◽  
Detection Accuracy ◽  
Single Shot ◽  
Ship Detection ◽  
Sar Imagery

Synthetic aperture radar (SAR) imagery has been used as a promising data source for monitoring maritime activities, and its application for oil and ship detection has been the focus of many previous research studies. Many object detection methods ranging from traditional to deep learning approaches have been proposed. However, majority of them are computationally intensive and have accuracy problems. The huge volume of the remote sensing data also brings a challenge for real time object detection. To mitigate this problem a high performance computing (HPC) method has been proposed to accelerate SAR imagery analysis, utilizing the GPU based computing methods. In this paper, we propose an enhanced GPU based deep learning method to detect ship from the SAR images. The You Only Look Once version 2 (YOLOv2) deep learning framework is proposed to model the architecture and training the model. YOLOv2 is a state-of-the-art real-time object detection system, which outperforms Faster Region-Based Convolutional Network (Faster R-CNN) and Single Shot Multibox Detector (SSD) methods. Additionally, in order to reduce computational time with relatively competitive detection accuracy, we develop a new architecture with less number of layers called YOLOv2-reduced. In the experiment, we use two types of datasets: A SAR ship detection dataset (SSDD) dataset and a Diversified SAR Ship Detection Dataset (DSSDD). These two datasets were used for training and testing purposes. YOLOv2 test results showed an increase in accuracy of ship detection as well as a noticeable reduction in computational time compared to Faster R-CNN. From the experimental results, the proposed YOLOv2 architecture achieves an accuracy of 90.05% and 89.13% on the SSDD and DSSDD datasets respectively. The proposed YOLOv2-reduced architecture has a similarly competent detection performance as YOLOv2, but with less computational time on a NVIDIA TITAN X GPU. The experimental results shows that the deep learning can make a big leap forward in improving the performance of SAR image ship detection.

scholarly journals Real-time human detection for electricity conservation using pruned-SSD and arduino

2021 ◽  
Vol 11 (2) ◽  
pp. 1510
Author(s):  
Ushasukhanya S. ◽  
Jothilakshmi S.
Keyword(s):  
Real Time ◽  
Power Supply ◽  
Computational Cost ◽  
Human Detection ◽  
Single Shot ◽  
Electric Power Supply ◽  
Tuning Method ◽  
Shot Detection ◽  
Average Accuracy ◽  
Electricity Conservation

Electricity conservation techniques have gained more importance in recent years. Many smart techniques are invented to save electricity with the help of assisted devices like sensors. Though it saves electricity, it adds an additional sensor cost to the system. This work aims to develop a system that manages the electric power supply, only when it is actually needed i.e., the system enables the power supply when a human is present in the location and disables it otherwise. The system avoids any additional costs by using the closed circuit television, which is installed in most of the places for security reasons. Human detection is done by a Modified-single shot detection with a specific hyperparameter tuning method. Further the model is pruned to reduce the computational cost of the framework which in turn reduces the processing speed of the network drastically. The model yields the output to the Arduino micro-controller to enable the power supply in and around the location only when a human is detected and disables it when the human exits. The model is evaluated on CHOKEPOINT dataset and real-time video surveillance footage. Experimental results have shown an average accuracy of 85.82% with 2.1 seconds of processing time per frame.

scholarly journals NSD-SSD: A Novel Real-Time Ship Detector Based on Convolutional Neural Network in Surveillance Video

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Jiuwu Sun ◽  
Zhijing Xu ◽  
Shanshan Liang
Keyword(s):  
Real Time ◽  
Clustering Algorithm ◽  
Detection Efficiency ◽  
Rapid Development ◽  
Outdoor Environment ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Single Shot ◽  
Ship Detection ◽  
Real Time Detection

With the rapid development of the marine industry, intelligent ship detection plays a very important role in the marine traffic safety and the port management. Current detection methods mainly focus on synthetic aperture radar (SAR) images, which is of great significance to the field of ship detection. However, these methods sometimes cannot meet the real-time requirement. To solve the problems, a novel ship detection network based on SSD (Single Shot Detector), named NSD-SSD, is proposed in this paper. Nowadays, the surveillance system is widely used in the indoor and outdoor environment, and its combination with deep learning greatly promotes the development of intelligent object detection and recognition. The NSD-SSD uses visual images captured by surveillance cameras to achieve real-time detection and further improves detection performance. First, dilated convolution and multiscale feature fusion are combined to improve the small objects’ performance and detection accuracy. Second, an improved prediction module is introduced to enhance deeper feature extraction ability of the model, and the mean Average Precision (mAP) and recall are significant improved. Finally, the prior boxes are reconstructed by using the K-means clustering algorithm, the Intersection-over-Union (IoU) is higher, and the visual effect is better. The experimental results based on ship images show that the mAP and recall can reach 89.3% and 93.6%, respectively, which outperforms the representative model (Faster R-CNN, SSD, and YOLOv3). Moreover, our model’s FPS is 45, which can meet real-time detection acquirement well. Hence, the proposed method has the better overall performance and achieves higher detection efficiency and better robustness.

scholarly journals Real-Time Depth-Based Hand Detection and Tracking

2014 ◽  
Vol 2014 ◽  
pp. 1-17 ◽  
Author(s):  
Sung-Il Joo ◽  
Sun-Hee Weon ◽  
Hyung-Il Choi
Keyword(s):  
Real Time ◽  
Mean Shift ◽  
Region Growing ◽  
Tracking Accuracy ◽  
Hand Detection ◽  
Seed Point ◽  
Mean Shift Algorithm ◽  
Detection And Tracking ◽  
Cascade Structure ◽  
Hand Region

This paper illustrates the hand detection and tracking method that operates in real time on depth data. To detect a hand region, we propose the classifier that combines a boosting and a cascade structure. The classifier uses the features of depth-difference at the stage of detection as well as learning. The features of each candidate segment are to be computed by subtracting the averages of depth values of subblocks from the central depth value of the segment. The features are selectively employed according to their discriminating power when constructing the classifier. To predict a hand region in a successive frame, a seed point in the next frame is to be determined. Starting from the seed point, a region growing scheme is applied to obtain a hand region. To determine the central point of a hand, we propose the so-called Depth Adaptive Mean Shift algorithm. DAM-Shift is a variant of CAM-Shift (Bradski, 1998), where the size of the search disk varies according to the depth of a hand. We have evaluated the proposed hand detection and tracking algorithm by comparing it against the existing AdaBoost (Friedman et al., 2000) qualitatively and quantitatively. We have analyzed the tracking accuracy through performance tests in various situations.

Real-time hand detection and tracking with depth values

2015 ◽  
Author(s):  
Md. Farhad Zaman ◽  
Samma Tasnim Mossarrat ◽  
Fahad Islam ◽  
Debajyoti Karmaker
Keyword(s):  
Real Time ◽  
Hand Detection ◽  
Detection And Tracking

scholarly journals Improved Accuracy of Vehicle Counter for Real-Time Traffic Monitoring System

2020 ◽  
Vol 21 (2) ◽  
pp. 125-133
Author(s):  
De Rosal Ignatius Moses Setiadi ◽  
Rizki Ramadhan Fratama ◽  
Nurul Diyah Ayu Partiningsih
Keyword(s):  
Real Time ◽  
Vehicle Detection ◽  
Traffic Monitoring ◽  
Previous Method ◽  
Detection Accuracy ◽  
Real Time Traffic ◽  
Detection And Tracking ◽  
Vehicle Detection And Tracking ◽  
Average Accuracy ◽  
Improved Accuracy

AbstractThis research proposes a background subtraction method with the truncate threshold to improve the accuracy of vehicle detection and tracking in real-time video streams. In previous research, vehicle detection accuracy still needs to be optimized, so it needed to be improved. In the vehicle detection method, there are several parts that greatly affect, one of which is the thresholding technique. Different thresholding methods can affect the results of the background and foreground separation. Based on the results of testing the proposed method can improve accuracy by more than 20% compared to the previous method. The thresholding method has a considerable influence on the final result of vehicle object detection. The results of the average accuracy of the three types of time, i.e. morning, daytime, and afternoon reached 96.01%. These results indicate that the vehicle counting accuracy is very satisfying, moreover, the method has also been implemented in a real way and can run smoothly.

Sign in / Sign up

Export Citation Format

Share Document