Computer vision & robotics engineer
I’m Arqam Imtiaz. I turn computer vision research into practical systems for robots, sports AI, and edge devices.
Years in computer
vision & robotics
Projects to
explore
From training pipelines
to deployed systems
01 /Selected work
A real-time, edge-powered tennis analytics stack combining player tracking, pose, ball trajectory, and court mapping.
View project detailsProprioception-only locomotion policies transferred from simulation to a custom quadruped across flat and rough terrain.
View project detailsA calibrated HD/4K tennis-perception pipeline that combines court pose, multi-branch temporal ball detection, size-derived ball depth, and person-depth predictions in shared 3D court coordinates.
View project detailsAn end-to-end instance-segmentation workflow spanning foundation-model auto-labeling, training, evaluation, and edge deployment.
View project detailsA synchronized LiDAR and multi-view pipeline that increased depth-label density from 6% to 58% through calibrated frame fusion.
View project detailsA lawn-care perception component that distills foundation-model masks and classifications into a compact weed detector.
View project details02 /In motion
Demonstrations from real projects. Watch the behavior, then explore the engineering behind it.
Benign Innovations
Project demonstration
Loads content from LinkedIn when you choose to play.A mounted-camera view of a tennis court includes overlaid court landmarks, player pose, ball positions, and a reconstructed trajectory. A court map summarizes the spatial view, and on-screen annotations indicate bounce events.
LinxAI Intelligent Technology
Project demonstration
Loads content from LinkedIn when you choose to play.The custom quadruped walks across physical test terrain using a policy based on proprioception. The video shows stairs, loose material, and changing support surfaces. The accompanying architecture diagram describes how training uses a privileged critic while the deployed actor uses robot observations.
Benign Innovations
Project demonstration
Loads content from LinkedIn when you choose to play.03 /Experience
Sports AI, autonomous robots, 3D vision, and the engineering that brings them into the real world.
Companies, roles & projects
Algorithm Engineer
Own the visual-perception lifecycle for real-time tennis AI systems.
Algorithm Engineer
Led applied perception R&D for tennis analytics and autonomous lawn-care robotics.
Algorithm Engineer
Developed deep-reinforcement-learning locomotion policies and simulation-to-robot transfer workflows.
Deep Learning Engineer
Built and optimized perception workflows across indoor 3D vision, robot interaction, and autonomous systems.
Research Assistant
Researched 3D scene parsing across semantic mesh segmentation and point-cloud object detection.
Algorithm Engineer
Developed real-time person re-identification and attribute-recognition systems for multi-camera environments.
Design Engineer
Contributed to smart-display graphics and EEG feature-extraction initiatives.
04 /Expertise
I work across the full ML lifecycle, connecting data quality, model behavior, hardware constraints, and product needs.
Real-time detection, tracking, temporal models, keypoints, segmentation, and multi-camera geometry.
Auto-labeling, active learning, hard-example mining, synthetic data, and quality auditing.
Training, benchmarking, ONNX and TensorRT export, quantization, profiling, monitoring, and iteration.
Depth, pose, point clouds, camera calibration, simulation-to-real transfer, and spatial perception.
05 /Education
Master of Engineering in Computer Technology
Thesis: Deep discriminative feature learning with a multi-level network for person re-identification.
Bachelor of Science in Electrical Engineering
Final project: vision-based shooting-target accuracy measurement for a training range.
HAVE A PROJECT OR AN OPPORTUNITY IN MIND?
Let’s talk about perception, a product challenge, or an idea worth exploring.
Start a conversation
