Computer vision engineer, deep learning, gen ai, iit kharagpur, Mtech
Resume:
Thomas Daniel Ardhali
M.Tech, Vision and Intelligent Systems
Department of Electronics and Communication Engineering Indian Institute of Technology, Kharagpur
****************@*****.***
linkedin.com/in/thomas-daniel-ardhali
Vizianagaram, Andhra Pradesh
SUMMARY
Computer Vision and Deep Learning engineer with hands-on experience in object detection, segmentation, optical flow, image restoration, and edge-oriented deployment. Strong foundation in Python, C++, PyTorch, OpenCV, and real-world vision pipelines, with project experience spanning multispectral perception, railway safety, OCR, motion analysis, and compression systems.
EDUCATION
• M.Tech in Vision and Intelligent Systems 2024 – 2026 Indian Institute of Technology, Kharagpur CGPA: 8.23/10
• B.Tech in Electronics and Communication Engineering 2020 – 2024 Maharaj Vijayaram Gajapathi Raj College of Engineering (Autonomous) CGPA: 8.16/10
• Board of Intermediate Education, Andhra Pradesh 2018 – 2020 Sri Chaitanya Junior College CGPA: 9.09/10
• Central Board of Secondary Education (X
th
) 2018 – 2019
Jawahar Navodaya Vidyalaya Percentage: 85.2%
RELEVANT COURSES
Image & Video Processing · Computer Vision · Deep Learning · Pattern Recognition & Machine Intelligence · Embedded Machine Learning · Statistical Signal Processing · Vision and Visualization · Multimedia Systems Design · Advanced Operating Systems · Data Structures & Algorithms
SKILLS
• Programming: Python, C++, C, SQL, Bash, Linux
• Computer Vision: Object Detection, Image Segmentation, Image Classification, Object Tracking, Optical Flow, Feature Detection & Matching, Camera Calibration, Homography Estimation, Stereo Geometry, Motion Analysis, Morphological Operations
• Deep Learning: PyTorch, TensorFlow, CNNs, YOLO, U-Net Variants, Vision Transformers, GANs, Transfer Learning, Knowledge Distillation, Mixed Precision Training (AMP)
• Deployment & Optimization: Model Quantization, INT8/FP16 Optimization, Edge Deployment, On-device Inference, Real-time Inference Pipelines, Model Compression, Latency Optimization, Memory-aware Design
• MLOps / Engineering: Docker, Git, GitHub, Weights & Biases, ONNX, FastAPI, Jupyter Notebook, Google Colab, VS Code
• Libraries / Frameworks: OpenCV, NumPy, Pandas, scikit-learn, C++ STL, LabelImg
• Image Processing: Spatial & Frequency Domain Filtering, DCT, Fourier Analysis, Colour Space Conversion
(RGB YCbCr/YUV), Noise Modelling, Image Restoration & Enhancement
• Data Engineering: Dataset Collection, Data Cleaning, COCO/VOC Annotation Formats, Class-balanced Augmentation, Custom Dataset Construction, Pseudo Ground Truth Generation
• Evaluation Metrics: mAP, IoU, Precision, Recall, Accuracy, PSNR, SSIM, LPIPS, BRISQUE, NIQE PROJECTS
• M.Tech Thesis — Deep Image Restoration for Real-World Lens Flare Suppression Aug 2024 – Mar 2026
IIT Kharagpur — Supervisor: Prof. Sudipta Mukhopadhyay
– Designed MFR-Net (Multi-scale Frequency-aware Residual Network) for real-world lens flare removal using FFT-based frequency attention, half-instance normalization, multi-scale residual learning, and physics-guided artifact subtraction.
– Benchmarked performance against Restormer, Uformer, HiNet, MPRNet, and U-Net on Flare7K++ and FlareReal600.
– Engineered UltraLightIRGhostUNet specifically for edge deployment using Ghost Convolutions, depthwise- separable decoding, IRTiny blocks, and ECA attention.
– Applied INT8/FP16 quantization, mixed precision training (AMP), and knowledge distillation to reduce model size and latency while preserving reconstruction quality.
– Evaluated using PSNR, SSIM, LPIPS, BRISQUE, and NIQE. AI-Powered Extreme Weather Vision, Obstacle Detection & Pilot Assistance System 2025 – 2026 Tooltech — Multispectral Vision — Radar-Camera Fusion — Railway Safety
– Developed a real-time multimodal computer vision system for railway and mining environments by integrating RGB cameras, thermal cameras, and radar sensors for robust obstacle detection under fog, dust, rain, glare, and low-visibility conditions.
– Built a YOLO-based object detection pipeline in PyTorch and OpenCV for pedestrian and obstacle detection under motion blur and long-range operational scenarios.
– Implemented semantic segmentation and virtual-fence logic for railway-track understanding, intrusion monitoring, and automated alert generation.
– Designed OpenCV-based camera calibration, homography estimation, and multi-sensor synchronization pipelines to improve localization accuracy and system reliability.
– Optimized preprocessing, inference, and sensor fusion pipelines for low-latency real-time deployment and field robustness on embedded edge hardware.
– Deployed optimized inference pipelines on NVIDIA Jetson AGX Orin 64GB using TensorRT acceleration, FP16 optimization, and asynchronous video processing workflows.
– Profiled runtime latency, GPU utilization, throughput, and memory efficiency across multiple deployment configurations for real-time edge inference.
• Real-Time Object Detection and Classification Pipeline 2024 – 2025 Academic Project — Deep Learning, IIT Kharagpur
– Built an end-to-end object detection and image classification pipeline using YOLO and CNN-based architectures in PyTorch.
– Prepared annotated datasets using LabelImg and COCO-format workflows with class-balanced augmentation including flipping, color jitter, and mosaic augmentation.
– Performed preprocessing, cleaning, analysis, training, and validation using OpenCV, NumPy, and Pandas.
– Evaluated performance using mAP, IoU, precision, recall, and failure-case analysis under occlusion and low- contrast conditions.
• OCR and Handwritten Digit Recognition Pipeline Aug 2024 – Oct 2025 Academic Project — Pattern Recognition, IIT Kharagpur
– Designed a ResNet9-based deep neural network for handwritten Optical character recognition.
– Curated a custom Telugu numeral dataset of 1,000+ images with diverse handwriting styles, demonstrating end-to-end dataset preparation and curation.
– Applied transfer learning using MNIST pretraining and fine-tuning on the custom dataset, achieving strong training and validation accuracy.
• Smart Retail Loss Prevention and Queue Analytics System 2025 – 2026 Real-Time Video Analytics — Edge AI
– Developed a real-time retail video analytics system for customer tracking, queue monitoring, and suspicious activity detection using multi-camera surveillance streams.
– Built low-latency object detection and multi-object tracking pipelines using YOLO-based detection models and ByteTrack for persistent identity tracking across crowded scenes.
– Implemented queue-length estimation, wait-time analytics, intrusion detection, and abandoned-object monitoring using temporal motion analysis and region-based event logic.
– Optimized inference pipelines using ONNX Runtime and TensorRT with Dockerized FastAPI deployment for scalable GPU-backed real-time inference.
– Integrated RTSP video streaming, asynchronous frame processing, inference logging, and experiment tracking using MLflow and Weights & Biases for production-oriented deployment monitoring.
• Optical Flow Estimation and Motion Analysis in Video 2024 – 2025 Academic Project — Computer Vision, IIT Kharagpur
– Estimated dense motion fields using block matching and Lucas–Kanade methods; fine-tuned FlowNetC and FlowNetS on FlyingChairs.
– Used OpenCV and PyTorch for frame processing, motion estimation, and flow-map generation.
– Built a custom video dataset with RAFT-generated pseudo ground truth for real-world motion analysis.
• JPEG Compression Codec — From-Scratch C++ Implementation 2024 – 2025 Academic Project — Image & Video Processing, IIT Kharagpur
– Implemented a fully functional JPEG encoder/decoder in C++ covering RGB to YCbCr conversion, 8 8 block DCT, quantization, zigzag scan, and Huffman entropy coding.
– Validated compression fidelity using PSNR and SSIM across multiple quality factors.
Contact this candidate