Portfolio

Vegetables Detection for Kitchen Arm Robot

Vegetables Detection using state-of-the-art-detectors (Yolov3, FRCNN, SSD): The project involves a custom real-time object detector to detect vegetables in the scene. I have trained the custom dataset using different state-of-the-art-detectors which are Yolov3, FRCNN, SSD and then test and compare the accuracy rate and time-efficiency of these algorithms.

Road Sign Tracking using Simple Online and Realtime Tracking with a Deep Association Metric (Deep SORT)

Deep Sort is a very fast and powerful tracking algorithm. It has been a practical way of approaching multiple object tracking problems. It uses the appearance information to track objects through occlusions and thereby reducing the identity switches. Performance evaluation and comparison has been performed on multiple object tracking using the Deep Sort algorithm in conjunction with the different state-of-the-art object detectors. Projects include Road Sign Tracking and People Tracking.

Road Sign Detection using Yolov2, Yolo-v3, FRCNN and SSD

This project presents road sign detection pipeline to detect road signs. Proposed several Deep Learning algorithms such as Yolov2, Yolo-v3, ResNet, Inception, VGG16 and fine-tuned model on datasets such as MS COCO and ImageNet for best accurate result.

Real-Time Facial Recognition System and Face Expression, Age, Gender Recognizer in the Web Browser

Developed a face recognition system based on CNN models that is able to identify faces and predict their gender, age and emotions in an image or video.

Publications

Comparison and study of Pedestrian Tracking using Deep SORT and state of the art detectors

doi: 10.17051/ilkonline.2021.05.889

Performance evaluation and comparison have been performed on pedestrian tracking using the Deep Sort algorithm in conjunction with the various state-of-the-art object detectors: YOLO, SSD and FasterRCNN. Criteria for Evaluation, datasets used for evaluation, along with the quantitative results have been described and discussed in this work.

Blog

I take some time off to work on things I'm passionate about. I write articles and publish them on the Internet. Below is a list of blogs that I wrote on machine learning.