The project collection
55 projects, with technical details, implementation notes, and demos. Browse by topic or company, or search for a specific system.
Trained and deployed seven-language TC-ResNet14 command models with 2–3-second audio windows and a shared TC-ResNet8 wake-word model with a 1-second window on ESP32-S3, using an INMP441 microphone.
View project detailsA completed synthetic speech data pipeline for keyword spotting across seven languages, combining voice design, identity-preserving cloning, ASR verification, and recoverable dataset assembly.
View project detailsA single-image YOLOv8 pose model combining person boxes, 17 body keypoints, camera-depth regression, and racket-hand recognition, with pose-derived free-hand gestures and RDK X5 export and inference.
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 detailsA three-frame ball detector with explicit diameter supervision, size-aware postprocessing, reviewed temporal datasets, and ONNX/TorchScript deployment paths.
View project detailsA SAM-3D-Body labeling workflow that produces person boxes, camera-depth estimates and hand-raise labels, followed by ReID-assisted role review, outlier handling and YOLO export.
View project detailsA single-image YOLO model with person boxes, a camera-depth regression head, and independent hand-raise and player-role classifiers, supported by reviewed teacher labels and edge export.
View project detailsA six-channel court detector that pairs RGB with a separate synthetic grid, predicts line–grid intersection landmarks, and reconstructs court lines for camera-pose estimation.
View project detailsAn extension of the three-frame ball detector with a dedicated distribution-regression branch that learns ball size alongside localization and frame identity.
View project detailsA raised-hand gesture component for tennis-machine stop control, first implemented separately and later consolidated into the shared person-attribute detector.
View project detailsA six-channel person detector that combines a current frame with a configurable earlier background frame, using matched crops and optional camera-motion compensation.
View project detailsA two-stage court-localization pipeline that detects seven court and net-post landmarks, then refines line and post cues in local crops for downstream camera geometry.
View project detailsA YOLO-based temporal detector that stacks three RGB frames into nine channels and returns frame-indexed ball detections, with full-frame and center-crop inference branches.
View project detailsA PyQt/SAM3 annotation workflow with multi-frame prompts, mask propagation, review and correction loops, and ISAT export in the original image coordinates.
View project detailsA dedicated CNN that estimates ball radius in crop-space pixels using distribution regression, with single-frame and paired-frame inputs for downstream camera-geometry calculations.
View project detailsA real-time, edge-powered tennis analytics stack combining player tracking, pose, ball trajectory, and court mapping.
View project detailsSynthetic tennis-court simulation work in Isaac Sim and Webots for generating ball-tracking datasets and testing camera layouts.
View project detailsA point-cloud processing pipeline for ground segmentation and obstacle extraction in outdoor robot navigation.
View project detailsAn object detection pipeline for a sprayer robot, from foundation-model auto-labeling to YOLOv11n edge deployment.
View project detailsA lawn-care perception component that distills foundation-model masks and classifications into a compact weed detector.
View project detailsA grass quality segmentation system that converts weak labels into patch-level supervision and produces quality heatmaps.
View project detailsA lightweight charging-station keypoint detector for 3D localization and auto-parking.
View project detailsA stereo matching pipeline that uses a large teacher model for auto-labeling and a smaller student model for edge deployment.
View project detailsAn end-to-end instance-segmentation workflow spanning foundation-model auto-labeling, training, evaluation, and edge deployment.
View project detailsA hierarchical quadruped locomotion framework that combines Deep Reinforcement Learning with Model Predictive Control.
View project detailsProprioception-only locomotion policies transferred from simulation to a custom quadruped across flat and rough terrain.
View project detailsDeep reinforcement learning experiments for quadruped locomotion on a Unitree A1 robot.
View project detailsA keypoint detection system for indoor doors and windows, designed to improve structural perception in indoor robotics environments.
View project detailsA binary semantic segmentation pipeline for separating a robotic arm from the background.
View project detailsAn RGB-D auto-labeling pipeline that generates 6-DoF grasp-pose annotations for robotic pick-and-place in unseen domestic environments.
View project detailsA survey and comparison of feature matching methods for visual odometry, visual localization, and SLAM.
View project detailsA custom human-object interaction dataset and model training workflow.
View project detailsA spatio-temporal action recognition project using contextual relationships between actions, people, and surrounding objects.
View project detailsA survey of human mesh reconstruction methods using parametric body models such as SMPL.
View project detailsA survey of recent facial expression recognition algorithms and emotion categories.
View project detailsA survey of 3D multi-person pose estimation methods for recovering human pose in both relative and absolute coordinate settings.
View project detailsA self-supervised multi-view stereo reconstruction workflow for generating stronger depth supervision on custom data.
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 stereo depth estimation project focused on modeling both aleatoric and epistemic uncertainty for safer real-time depth prediction.
View project detailsAdded real-time aleatoric uncertainty estimation to a semantic segmentation pipeline so uncertain regions can be filtered before downstream use.
View project detailsAn indoor semantic segmentation project comparing transformer-based and CNN-based segmentation models on custom robotics data.
View project detailsAn indoor 3D perception pipeline combining stereo depth, 3D object detection, and 6D pose estimation.
View project detailsA human attributes recognition system focused on safety-related visual attributes and edge deployment.
View project detailsA real-time person re-identification system for intelligent video surveillance across six adjacent-street cameras.
View project detailsMaster's thesis on deep discriminative feature learning for person re-identification.
View project detailsExplored Generative Adversarial Networks for synthetic image generation using the classic generator-discriminator training setup.
View project detailsContributed to the graphics software for a smart multi-function display using OpenGL.
View project detailsContributed to an EEG-based system for mental state and emotion classification.
View project detailsA computer vision system for measuring shooting target accuracy and managing shooter records.
View project detailsA single-cycle processor designed in Verilog for a computer organization and architecture course.
View project detailsAn embedded system that extracts navigation information from a GPS receiver using an 8051 microcontroller.
View project detailsAn 8051 microcontroller-based distance measurement system designed as a movement orientation aid for dark or low-visibility environments.
View project detailsA hardware-based digital dice circuit that generates random dice values and displays them on a 7-segment display.
View project detailsA Java Sudoku game developed for an object-oriented programming course, with a graphical interface and event-driven interaction.
View project detailsA compact C-language Tic Tac Toe game built as an Introduction to Computer Programming course project.
View project detailsTry fewer words, another topic, or clear the filters to explore everything.
Want the context behind the work?
Explore experience by company
