scholarly journals Frame Prediction- Noise Removal using Denoising Autoencoders

2019 ◽  
Vol 9 (2) ◽  
pp. 5296-5299
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Object Detection ◽  
Object Tracking ◽  
Noise Removal ◽  
Video Frame ◽  
Previous Frame ◽  
Improved Accuracy ◽  
Video Prediction

In the current times, tasks like Object Detection, Object tracking, Gesture prediction, Video prediction in computer vision are being solved effectively with models of deep learning . Video frame prediction involves predicting the next few frames of a video given the previous frame or frames as input. Currently, the challenge in video frame prediction is that the predicted future frames are blurry. This paper focuses on the removal of noise from the predicted image using Denoising Autoencoders, solve the above-addressed issue. The proposed work, trains LSTM model which generates future frames by giving a sequence of input frames. The predicted output is given as an input to the Denoising Autoencoders which tries to remove the blurry predictions. Our approach is implemented on Moving MNIST Dataset. The result of our proposed method improved accuracy and is compared with the accuracy of Denoising Autoencoders, LSTM, and LSTM along with Denoising Autoencoders

scholarly journals Efficient Single-Shot Multi-Object Tracking for Vehicles in Traffic Scenarios

Sensors ◽  
2021 ◽  
Vol 21 (19) ◽  
pp. 6358
Author(s):  
Youngkeun Lee ◽  
Sang-ha Lee ◽  
Jisang Yoo ◽  
Soonchul Kwon
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Object Tracking ◽  
State Of The Art ◽  
Tracking System ◽  
Single Shot ◽  
Essential Information ◽  
Trade Off ◽  
Previous State ◽  
Improved Accuracy

Multi-object tracking is a significant field in computer vision since it provides essential information for video surveillance and analysis. Several different deep learning-based approaches have been developed to improve the performance of multi-object tracking by applying the most accurate and efficient combinations of object detection models and appearance embedding extraction models. However, two-stage methods show a low inference speed since the embedding extraction can only be performed at the end of the object detection. To alleviate this problem, single-shot methods, which simultaneously perform object detection and embedding extraction, have been developed and have drastically improved the inference speed. However, there is a trade-off between accuracy and efficiency. Therefore, this study proposes an enhanced single-shot multi-object tracking system that displays improved accuracy while maintaining a high inference speed. With a strong feature extraction and fusion, the object detection of our model achieves an AP score of 69.93% on the UA-DETRAC dataset and outperforms previous state-of-the-art methods, such as FairMOT and JDE. Based on the improved object detection performance, our multi-object tracking system achieves a MOTA score of 68.5% and a PR-MOTA score of 24.5% on the same dataset, also surpassing the previous state-of-the-art trackers.

Social Distancing Using AI and Deep Learning

2021 ◽  
Vol 9 (VII) ◽  
pp. 1816-1822
Author(s):  
Mr. Kiran Mudaraddi
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Open Source ◽  
Suggested Method ◽  
Video Frame ◽  
Social Distancing ◽  
The Social ◽  
The Impact

The paper presents a deep learning-based methodology for detecting social distancing in order to assess the distance between people in order to mitigate the impact of the coronavirus pandemic. The input was a video frame from the camera, and the open-source object detection was pre-trained. The outcome demonstrates that the suggested method is capable of determining the social distancing measures between many participants in a video.

scholarly journals Deep Learning Based Switching Filter for Impulsive Noise Removal in Color Images

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2782
Author(s):  
Krystian Radlak ◽  
Lukasz Malinski ◽  
Bogdan Smolka
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Network Architecture ◽  
Noise Suppression ◽  
Impulsive Noise ◽  
Noise Removal ◽  
Vision Systems ◽  
Mean Filter ◽  
Computer Vision Systems ◽  
Active Research

Noise reduction is one of the most important and still active research topics in low-level image processing due to its high impact on object detection and scene understanding for computer vision systems. Recently, we observed a substantially increased interest in the application of deep learning algorithms. Many computer vision systems use them, due to their impressive capability of feature extraction and classification. While these methods have also been successfully applied in image denoising, significantly improving its performance, most of the proposed approaches were designed for Gaussian noise suppression. In this paper, we present a switching filtering technique intended for impulsive noise removal using deep learning. In the proposed method, the distorted pixels are detected using a deep neural network architecture and restored with the fast adaptive mean filter. The performed experiments show that the proposed approach is superior to the state-of-the-art filters designed for impulsive noise removal in color digital images.

scholarly journals Salient Object Detection Techniques in Computer Vision—A Survey

Entropy ◽  
2020 ◽  
Vol 22 (10) ◽  
pp. 1174
Author(s):  
Ashish Kumar Gupta ◽  
Ayan Seal ◽  
Mukesh Prasad ◽  
Pritee Khanna
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Object Detection ◽  
Large Scale ◽  
Research Work ◽  
Salient Object Detection ◽  
Future Research ◽  
Automatic Identification ◽  
Salient Object ◽  
Detection Techniques

Detection and localization of regions of images that attract immediate human visual attention is currently an intensive area of research in computer vision. The capability of automatic identification and segmentation of such salient image regions has immediate consequences for applications in the field of computer vision, computer graphics, and multimedia. A large number of salient object detection (SOD) methods have been devised to effectively mimic the capability of the human visual system to detect the salient regions in images. These methods can be broadly categorized into two categories based on their feature engineering mechanism: conventional or deep learning-based. In this survey, most of the influential advances in image-based SOD from both conventional as well as deep learning-based categories have been reviewed in detail. Relevant saliency modeling trends with key issues, core techniques, and the scope for future research work have been discussed in the context of difficulties often faced in salient object detection. Results are presented for various challenging cases for some large-scale public datasets. Different metrics considered for assessment of the performance of state-of-the-art salient object detection models are also covered. Some future directions for SOD are presented towards end.

Comparison of Object Detection Methods for Corn Damage Assessment Using Deep Learning

2020 ◽  
Vol 63 (6) ◽  
pp. 1969-1980
Author(s):  
Ali Hamidisepehr ◽  
Seyed V. Mirnezami ◽  
Jason K. Ward
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Object Detection ◽  
Damage Detection ◽  
Damage Identification ◽  
Severe Weather ◽  
Crop Damage ◽  
Growth Stages ◽  
List Type ◽  
Data Set

HighlightsCorn damage detection was possible using advanced deep learning and computer vision techniques trained with images of simulated corn lodging.RetinaNet and YOLOv2 both worked well at identifying regions of lodged corn.Automating crop damage identification could provide useful information to producers and other stakeholders from visual-band UAS imagery.Abstract. Severe weather events can cause large financial losses to farmers. Detailed information on the location and severity of damage will assist farmers, insurance companies, and disaster response agencies in making wise post-damage decisions. The goal of this study was a proof-of-concept to detect areas of damaged corn from aerial imagery using computer vision and deep learning techniques. A specific objective was to compare existing object detection algorithms to determine which is best suited for corn damage detection. Simulated corn lodging was used to create a training and analysis data set. An unmanned aerial system equipped with an RGB camera was used for image acquisition. Three popular object detectors (Faster R-CNN, YOLOv2, and RetinaNet) were assessed for their ability to detect damaged areas. Average precision (AP) was used to compare object detectors. RetinaNet and YOLOv2 demonstrated robust capability for corn damage identification, with AP ranging from 98.43% to 73.24% and from 97.0% to 55.99%, respectively, across all conditions. Faster R-CNN did not perform as well as the other two models, with AP between 77.29% and 14.47% for all conditions. Detecting corn damage at later growth stages was more difficult for all three object detectors. Keywords: Computer vision, Faster R-CNN, RetinaNet, Severe weather, Smart farming, YOLO.

scholarly journals Ball Classification through Object Detection using Deep Learning for Handball

Mekatronika ◽  
2020 ◽  
Vol 2 (2) ◽  
pp. 49-54
Author(s):  
Arzielah Ashiqin Alwi ◽  
Ahmad Najmuddin Ibrahim ◽  
Muhammad Nur Aiman Shapiee ◽  
Muhammad Ar Rahim Ibrahim ◽  
Mohd Azraai Mohd Razman ◽  
...  
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Deep Learning ◽  
Performance Analysis ◽  
Object Detection ◽  
High Speed ◽  
Detection Accuracy ◽  
Narrow Angle ◽  
Target Locations ◽  
Ball Detection

Dynamic gameplay, fast-paced and fast-changing gameplay, where angle shooting (top and bottom corner) has the best chance of a good goal, are the main aspects of handball. When it comes to the narrow-angle area, the goalkeeper has trouble blocked the goal. Therefore, this research discusses image processing to investigate the shooting precision performance analysis to detect the ball's accuracy at high speed. In the handball goal, the participants had to complete 50 successful shots at each of the four target locations. Computer vision will then be implemented through a camera to identify the ball, followed by determining the accuracy of the ball position of floating, net tangle and farthest or smallest using object detection as the accuracy marker. The model will be trained using Deep Learning (DL)  models of YOLOv2, YOLOv3, and Faster R-CNN and the best precision models of ball detection accuracy were compared. It was found that the best performance of the accuracy of the classifier Faster R-CNN produces 99% for all ball positions.

scholarly journals Fast and Economical Object Tracking using Raspberry Pi 3.0

2019 ◽  
Vol 8 (6S) ◽  
pp. 336-338
Keyword(s):  
Computer Vision ◽  
Power Consumption ◽  
Low Power ◽  
Object Detection ◽  
Object Tracking ◽  
Tracking System ◽  
Low Power Consumption ◽  
Raspberry Pi ◽  
Multiple Object Detection ◽  
Vision Application

This paper proposes a way to construct a financially cheap and fast object tracking using Raspberry Pi3. Multiple object detection is an important step in any computer vision application. Since the number of cameras included is more these gadgets are compelled by expense per hub, control utilization and handling power. We propose a tracking system with low power consumption. The framework is completely designed with python and OpenCV. The tracking quality and accuracy is measured using publicly available datasets.

Weapon and Object Detection Using Mobile-Net SSD Model in Deep Neural Network

2021 ◽  
Vol 9 (8) ◽  
pp. 1573-1582
Author(s):  
S Gopi Naik
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Deep Learning ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Optimization Algorithms ◽  
Object Identification ◽  
Integrated System ◽  
Raspberry Pi ◽  
High Level

Abstract: The plan is to establish an integrated system that can manage high-quality visual information and also detect weapons quickly and efficiently. It is obtained by integrating ARM-based computer vision and optimization algorithms with deep neural networks able to detect the presence of a threat. The whole system is connected to a Raspberry Pi module, which will capture live broadcasting and evaluate it using a deep convolutional neural network. Due to the intimate interaction between object identification and video and image analysis in real-time objects, By generating sophisticated ensembles that incorporate various low-level picture features with high-level information from object detection and scenario classifiers, their performance can quickly plateau. Deep learning models, which can learn semantic, high-level, deeper features, have been developed to overcome the issues that are present in optimization algorithms. It presents a review of deep learning based object detection frameworks that use Convolutional Neural Network layers for better understanding of object detection. The Mobile-Net SSD model behaves differently in network design, training methods, and optimization functions, among other things. The crime rate in suspicious areas has been reduced as a consequence of weapon detection. However, security is always a major concern in human life. The Raspberry Pi module, or computer vision, has been extensively used in the detection and monitoring of weapons. Due to the growing rate of human safety protection, privacy and the integration of live broadcasting systems which can detect and analyse images, suspicious areas are becoming indispensable in intelligence. This process uses a Mobile-Net SSD algorithm to achieve automatic weapons and object detection. Keywords: Computer Vision, Weapon and Object Detection, Raspberry Pi Camera, RTSP, SMTP, Mobile-Net SSD, CNN, Artificial Intelligence.

Sign in / Sign up

Export Citation Format

Share Document