Junsheng Fu

tracking-with-Extended-Kalman-Filter. Object (e.g Pedestrian, vehicles) tracking by Extended Kalman Filter (EKF), with fused data from both lidar and radar sensors.

vehicle-detection. Created vehicle detection pipeline with two approaches: (1) deep neural networks (YOLO framework) and (2) support vector machines ( OpenCV + HOG).

driving-lane-departure-warning. Built a real-time lane departure warning system with a monocular camera, using OpenCV.

Model-Predictive-Control. This project is to use Model Predictive Control (MPC) to drive a car in a game simulator. The server provides reference waypoints (yellow line in the demo video) via websocket, and we use MPC to compute steering and throttle commands to drive the car. The solution must be robust to 100ms latency, since it might encounter in real-world application.

tracking-with-Unscented-Kalman-Filter. Object (e.g Pedestrian, biker, vehicles) tracking by Unscented Kalman Filter (UKF), with fused data from both lidar and radar sensors.

semantic_segmentation. Semantically segment the road in the given image.

traffic-light-detector. Detect traffic lights and classify the state of them, then give the commands "go" or "stop".

PID-controller. Use a PID controller to control the steering angle and throttle for driving a car in a car game simulator.

camera-pose-estimation. Given a map data (image + lidar), estimate the 6 DoF camera pose of the query image.

path_planning. Implement a simple real-time path planner in C++ to navigate a car around a simulated highway scenario

kidnapped-vehicle. Implemented a C++ particle filter for real-time vehicle localization with only current visual observations and a map.

traffic-light-classifier. A simple network to classifier the states of the traffic lights.

DrivingLaneDetection. Detected highway lane lines on a video stream. Used OpencV image analysis techniques to identify lines, including Hough Transforms and Canny edge detection.

driving-behavioral-cloning. Built and trained a convolutional neural network for end-to-end driving in a simulator, using TensorFlow and Keras.

traffic-sign-recognition. Built and trained a deep neural network to classify traffic signs, using TensorFlow.

calculator. C++ based Calculation Engines which can do multiplication and division with numbers, and it is implemented with template and factory method.

rental-bike. Predict the number of rental bikes should be placed based on the environmental conditions.

ResNet_MobileNet_InceptionV3. An example to run ResNet, MobileNet and InceptionV3 with Keras and Imagenet weights