Rajat-Mehta
Machine Learning Engineer working on Autonomous Vehicles | Computer Vision | Deep Learning | Sensor Fusion | Machine Learning
TU KaiserslauternGermany
Pinned Repositories
Deep_Object_Pose
Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)
Einburgerungstest
Complete catalog of questions and answers for the test "Leben in Deutschland" and "Einbürgerungstest"
kmeans_pytorch
pytorch implementation of basic kmeans algorithm(lloyd method with forgy initialization) with gpu support
MachineLearning-CourseEra
Object-Tracking-Extended-Kalman-Filter-Sensor-Fusion
Object (e.g Pedestrian, vehicles) tracking by Extended Kalman Filter (EKF), with fused data from both lidar and radar sensors.
Object-Tracking-Unscented-Kalman-Filter-Sensor-Fusion
Object (e.g Pedestrian, biker, vehicles) tracking by Unscented Kalman Filter (UKF), with fused data from both lidar and radar sensors.
Person-reID-triplet-loss
Person re-ID baseline with triplet loss
person-reid-triplet-loss-baseline
Rank-1 89% (Single Query) on Market1501 with raw triplet loss, In Defense of the Triplet Loss for Person Re-Identification, using Pytorch
ReID-PCB_RPP
Beyond Part Models: Person Retrieval with Refined Part Pooling
Vehicle-Re-identification-UI
ui for vehicle re-id
Rajat-Mehta's Repositories
Rajat-Mehta/Vehicle-Re-identification-UI
ui for vehicle re-id
Rajat-Mehta/Deep_Object_Pose
Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)
Rajat-Mehta/Einburgerungstest
Complete catalog of questions and answers for the test "Leben in Deutschland" and "Einbürgerungstest"
Rajat-Mehta/kmeans_pytorch
pytorch implementation of basic kmeans algorithm(lloyd method with forgy initialization) with gpu support
Rajat-Mehta/MachineLearning-CourseEra
Rajat-Mehta/Object-Tracking-Extended-Kalman-Filter-Sensor-Fusion
Object (e.g Pedestrian, vehicles) tracking by Extended Kalman Filter (EKF), with fused data from both lidar and radar sensors.
Rajat-Mehta/Object-Tracking-Unscented-Kalman-Filter-Sensor-Fusion
Object (e.g Pedestrian, biker, vehicles) tracking by Unscented Kalman Filter (UKF), with fused data from both lidar and radar sensors.
Rajat-Mehta/Person-reID-triplet-loss
Person re-ID baseline with triplet loss
Rajat-Mehta/person-reid-triplet-loss-baseline
Rank-1 89% (Single Query) on Market1501 with raw triplet loss, In Defense of the Triplet Loss for Person Re-Identification, using Pytorch
Rajat-Mehta/ReID-PCB_RPP
Beyond Part Models: Person Retrieval with Refined Part Pooling
Rajat-Mehta/SA-SSD
Rajat-Mehta/SIGNS_Resnet
Recognizing signs dataset with Resnet architecture
Rajat-Mehta/singleshotpose
This research project implements a real-time object detection and pose estimation method as described in the paper, Tekin et al. "Real-Time Seamless Single Shot 6D Object Pose Prediction", CVPR 2018. (https://arxiv.org/abs/1711.08848).
Rajat-Mehta/Udacity-SensorFusion-NanoDegree
This is my Sensor Fusion projects with Udacity ND.
Rajat-Mehta/Vehicle-Detection-With-Ensembling
Model ensembling approach for Vehicle detection and localization
Rajat-Mehta/yolov3
YOLOv3 in PyTorch > ONNX > CoreML > iOS