Chapters by M T Gopalakrishna
International Journal of Latest Research in Engineering and Technology (IJLRET), 2016
The demand for automatic action recognition systems have increased due to the rapid increase in t... more The demand for automatic action recognition systems have increased due to the rapid increase in the number of video surveillance cameras installed in cities and towns. Automatic action recognition system can be effectively used to generate on-line alarm in case of abnormal activities to assist human operators and for offline inspection. Although action recognition problem has become a hot topic within computer vision, detection of violent scenes receives considerable attention in surveillance system which is justified by the need of providing people with safer public spaces. This survey discusses the current state of the art methods and techniques that are being applied for the task of automated violence detection.This survey emphasizes on motivation and challenges of this very recent research area by presenting approaches for violence recognition in surveillance video. This paper aims at being a driving force for researchers who wish to approach the study of violent activity recognition and gather insights on the main challenges to solve in this emerging field.
ISSR: Intensity Slicing and Spatial Resolution Approaches for Moving Object Detection and Tracking under Litter Background
Springer Berlin Heidelberg, 2013
Moving object Detection in video sequences is one among the foremost indispensable challenges in ... more Moving object Detection in video sequences is one among the foremost indispensable challenges in Image and video processing. Its conjoint research areas are activity monitoring and video surveillance application. However, still beneath the biological process stage needs robust approaches once applied in an unconstrained environment. Several detection algorithms have higher performance under the static background, however decline results under background with fake motions. Detecting and Tracking of multiple moving objects in presence of Litter background like leaves movement of trees, water waves, fountain, window curtain movement and change of illumination in video sequences is a challenging problem. Because of these little movements within the background, it affects the performance of the automated tracking system. To overcome the above said problem, an approach consisting of Intensity Slicing and Spatial Resolution is considered to attenuate the results caused by the Litter Background. A modified 3-frame difference technique is employed to detect a moving object. Then, Adaptive Thresholding is used to segment the object from the background and to track the object. Results are compared with the existing well known traditional techniques. The proposed technique is tested on standard PETS datasets and our own collected video datasets. The experimental results prove the feasibility and usefulness of the proposed technique.
Ten-LoPP: Tensor Locality Preserving Projections Approach for Moving Object Detection and Tracking
Springer Berlin Heidelberg, 2013
In recent years, automatic moving object detection and tracking is a challenging task for many co... more In recent years, automatic moving object detection and tracking is a challenging task for many computer vision applications such as video surveillance, traffic monitoring and activity analysis. In this regard, many methods have been proposed based on different approaches. Despite of its importance, moving object detection and tracking in complex environments is still far from being completely solved for low resolution videos, foggy videos, and also Infrared video sequences. A novel scheme for Moving Object detection based on Tensor Locality Preserving Projections (Ten-LoPP) approach is proposed. Consequently, a Moving Object is tracked based on the centroid and area of a detected object. Numbers of experiments are conducted for indoor and outdoor video sequences of standard PETS, OTCBVS, Videoweb Activities datasets and also our own collected video sequences comprising partial night vision video sequences. Results obtained are satisfactory and competent. Comparative study is performed with existing well known traditional subspace learning methods.
Multiple Moving Object Recognitions in Video Based on Log Gabor-PCA Approach
Object recognition in the video sequence or images is one of the subfield of computer vision. Mov... more Object recognition in the video sequence or images is one of the subfield of computer vision. Moving object recognition from a video sequence is an appealing topic with applications in various areas such as airport safety, intrusion surveillance, video monitoring, intelligent highway, etc. Moving object recognition is the most challenging task in intelligent video surveillance system. In this regard, many techniques have been proposed based on different methods. Despite of its importance, moving object recognition in complex environments is still far from being completely solved for low resolution videos, foggy videos, and also dim video sequences. All in all, these make it necessary to develop exceedingly robust techniques. This paper introduces multiple moving object recognition in the video sequence based on LoG Gabor-PCA approach and Angle based distance Similarity measures techniques used to recognize the object as a human, vehicle etc. Number of experiments are conducted for indoor and outdoor video sequences of standard datasets and also our own collection of video sequences comprising of partial night vision video sequences. Experimental results show that our proposed approach achieves an excellent recognition rate. Results obtained are satisfactory and competent.
Papers by M T Gopalakrishna
Foreground Segmentation Network using Transposed Convolutional Neural Networks and Up sampling for Multiscale Feature Encoding
Neural Networks, Jan 31, 2024
Text Detection and Recognition from the Scene Images Using RCNN and EasyOCR
Lecture notes in networks and systems, Dec 31, 2022
Dynamic Background Modeling and Foreground Detection using Orthogonal Projection onto the Subspace of Moving Objects
Deep Learning-Based Diagnosis of Lung Abnormalities on X-ray images: A Comparative Study of U-Net and Sequential CNN Models
Comparative Analysis of Traditional Classification and Deep Learning in Lung Cancer Prediction
Biomedical Engineering: Applications, Basis and Communications
The cancer is an intimidating illness. Extra care is necessary while making a diagnosis. To aid t... more The cancer is an intimidating illness. Extra care is necessary while making a diagnosis. To aid the identification process, medical imaging plays a crucial role by producing images of the internal organs of the body for better diagnosis of cancer. Medical images are typically utilized by radiologists, engineers, and clinicians to spot the inner constitution of either individual patients or group of individuals. Most doctors prefer computed tomography (CT) images for initial screening of cancer — mainly lung cancer. To achieve deeper understanding and categorization of lung cancer, diverse machine learning techniques are employed in image classification. Many research works have been done on the classification of CT images with different algorithms, but they failed to reach 100% accuracy. By applying methods like Support Vector Machine, deep learning system like artificial neural network (ANN) and proposed convolution neural network (CNN), a computerized system can be built for truth...
Application of Deep Learning in Detection of Covid-19 Face Mask
Smart innovation, systems and technologies, 2022
Automated Violence Detection in Video Crowd Using Spider Monkey-Grasshopper Optimization Oriented Optimal Feature Selection and Deep Neural Network
Journal of Control, Automation and Electrical Systems
Discriminatively Trained Multi-source CNN Model for Multi-camera Based Vehicle Tracking Under Occlusion Conditions
Smart innovation, systems and technologies, 2020
In this paper, a novel Discriminatively Trained Multi-Source CNN Model (DTM-CNN) is developed for... more In this paper, a novel Discriminatively Trained Multi-Source CNN Model (DTM-CNN) is developed for multi-camera based vehicle tracking purpose. DTM-CNN performs pretraining of a gigantically large set of traffic videos to track ground truths for retaining region of interest (ROI) representation. Being a multi-source tracking method DTM-CNN embodies shared layers and multiple branches of source-specific layers to perform feature extraction and training. Here, source signifies each camera input with distinct training sequences, where each branch exhibits binary classification for ROI identification and tracking in each source. DTM-CNN trains each source input iteratively to achieve generic ROI representations in the shared layers. When performing tracking in a new sequence, DTM-CNN forms a new network by combining the shared layers with a new binary classification layer, which is updated online. It assists online tracking by retrieving the ROI windows arbitrarily sampled near the previous ROI state that enables DTM-CNN to exhibit continuous vehicle tracking even under short and long term occlusion.
ResNet50-YOLOv2-Convolutional Neural Network Based Hybrid Deep Structural Learning for Moving Vehicle Tracking under Occlusion
Solid State Technology, Oct 16, 2020
The demand for automatic action recognition systems have increased due to the rapid increase in t... more The demand for automatic action recognition systems have increased due to the rapid increase in the number of video surveillance cameras installed in cities and towns. Automatic action recognition system can be effectively used to generate on-line alarm in case of abnormal activities to assist human operators and for offline inspection. Although action recognition problem has become a hot topic within computer vision, detection of violent scenes receives considerable attention in surveillance system which is justified by the need of providing people with safer public spaces. This survey discusses the current state of the art methods and techniques that are being applied for the task of automated violence detection.This survey emphasizes on motivation and challenges of this very recent research area by presenting approaches for violence recognition in surveillance video. This paper aims at being a driving force for researchers who wish to approach the study of violent activity recogn...
Vision-based traffic surveillance has been one of the most promising fields for improvement and r... more Vision-based traffic surveillance has been one of the most promising fields for improvement and research. Still, many challenging problems remain unsolved, such as addressing vehicle occlusions and reducing false detection. In this work, a method for vehicle detection and tracking is proposed. The proposed model considers background subtraction concept for moving vehicle detection but unlike conventional approaches, here numerous algorithmic optimization approaches have been applied such as multi-directional filtering and fusion based background subtraction, thresholding, directional filtering and morphological operations for moving vehicle detection. In addition, blob analysis and adaptive bounding box is used for Detection and Tracking. The Performance of Proposed work is measured on Standard Dataset and results are encouraging. __________________________________________________________________________
J. Multim. Process. Technol., 2016
Visual Surveillance systems have greatly increased in past few years. Several methods have been p... more Visual Surveillance systems have greatly increased in past few years. Several methods have been proposed in order to improve the efficiency of Face Detection but still remains a challenging task due to various illumination, poses and occlusion conditions. In this paper, we propose a novel method for Face Detection where a decision boundary is defined for skin classifier based on training dataset. Log-Gabor filter is used for feature extraction which is superior to Gabor filter as they can represent better frequency properties of the objects present in the video and SVM classifier is used for classifying it as face or non-face. The proposed method is tested on standard and our own collected video sequences, which shows good tolerance and is better than those of existing related algorithms.
A Detailed Review of Color Image Contrast Enhancement Techniques for Real Time Applications
Advances in Intelligent Systems and Computing, 2016
Real-time video surveillance, medical imaging, industrial automation and oceanography application... more Real-time video surveillance, medical imaging, industrial automation and oceanography applications use image enhancement as a preprocessing technique for the analysis of images. Contrast enhancement is one of a method to enhance low contrast images obtained under poor lighting and fog conditions. In this paper, various variants of histogram equalisation, Homomorphic filtering and dark channel prior techniques used for image enhancement are reviewed and presented. Real-time processing of images is implemented on Field Programmable Gate Array (FPGA) to increase the computing speed. Further this paper focus on the review of contrast enhancement techniques implemented on FPGA in terms of device utilization and processing time.
i-Door: Intelligent Door Based on Smart Phone
Advances in Intelligent Systems and Computing, 2015
ABSTRACT Face recognition system have been widely developed. The machine vision system becomes an... more ABSTRACT Face recognition system have been widely developed. The machine vision system becomes an interest of many researchers in various fields of science. It provides the most important characteristic of natural interaction that is personalization. Automatic face recognition is a challenging problem, since human faces have a complex pattern. This paper presents a method for recognition of frontal human faces on gray scale images. The system is developed so that user can access the room just stand in front of the webcam. The webcam will send the image captured to the computer for recognition. In the proposed method, Discrete Cosine Transform (DCT) is used to extract the facial feature of an image the distance between the of the test image and train I and Euclidean Classifier is used to for the selection of best match between test image and trained image that has already been stored in database. When match occurred, computer will send signal to the microcontroller to open the lock through UART, else computer will send the unrecognized image to the owner’s mobile. When owner wants to open the door for the visitor then, using his mobile owner will send signal to the microcontroller to unlock the door. This paper will develop an intelligent door based on smart phone that can be implemented in real-life applications.
Comprehensive Review of Video Enhancement Algorithms for Low Lighting Conditions
Advances in Intelligent Systems and Computing, 2016
Video enhancement becomes a very challenging problem under low lighting conditions. Numerous tech... more Video enhancement becomes a very challenging problem under low lighting conditions. Numerous techniques for enhancing visual quality of videos/images captured under different environmental situations are proposed by number of researchers especially in dark or night time, foggy situations, rainy and so on. This paper discusses brief review of existing algorithms related to video enhancement techniques under various lighting condition such as De-hazing based enhancement algorithm, a novel integrated algorithm, gradient based fusion algorithm and dark channel prior and in addition it also presents advantages and disadvantages of these algorithms.
Uploads
Chapters by M T Gopalakrishna
Papers by M T Gopalakrishna