Search Results for author: Pratik Chattopadhyay

Found 7 papers, 0 papers with code

Gait Cycle Reconstruction and Human Identification from Occluded Sequences

no code implementations20 Jun 2022 Abhishek Paul, Manav Mukesh Jain, Jinesh Jain, Pratik Chattopadhyay

Gait-based person identification from videos captured at surveillance sites using Computer Vision-based techniques is quite challenging since these walking sequences are usually corrupted with occlusion, and a complete cycle of gait is not always available.

Gait Recognition Occlusion Handling +1

An Improved Deep Learning Approach For Product Recognition on Racks in Retail Stores

no code implementations26 Feb 2022 Ankit Sinha, Soham Banerjee, Pratik Chattopadhyay

Each of the models is fine-tuned using appropriate data sets for better prediction and data augmentation is performed on each query image to prepare an extensive gallery set for fine-tuning the ResNet-18-based product recognition model.

Data Augmentation Object +2

Deep Learning based Person Re-identification

no code implementations7 May 2020 Nirbhay Kumar Tagore, Ayushman Singh, Sumanth Manche, Pratik Chattopadhyay

Automated person re-identification in a multi-camera surveillance setup is very important for effective tracking and monitoring crowd movement.

Person Re-Identification

RGait-NET: An Effective Network for Recovering Missing Information from Occluded Gait Cycles

no code implementations14 Dec 2019 Dhritimaan Das, Ayush Agarwal, Pratik Chattopadhyay, Lipo Wang

Over the past decade, several computer vision-based gait recognition approaches have been proposed in which walking information corresponding to a complete gait cycle has been used to construct gait features for person identification.

Gait Recognition Occlusion Handling +1

Fully Automated Image De-fencing using Conditional Generative Adversarial Networks

no code implementations19 Aug 2019 Divyanshu Gupta, Shorya Jain, Utkarsh Tripathi, Pratik Chattopadhyay, Lipo Wang

Image de-fencing is one of the important aspects of recreational photography in which the objective is to remove the fence texture present in an image and generate an aesthetically pleasing version of the same image without the fence texture.

Image Generation Image Reconstruction

Broad Neural Network for Change Detection in Aerial Images

no code implementations28 Feb 2019 Shailesh Shrivastava, Alakh Aggarwal, Pratik Chattopadhyay

Since pixel-based analysis can be erroneous due to noise, illumination difference and other factors, contextual information is usually used to determine the class of a pixel (changed or not).

Change Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.