Underwater-Robotics

Development of underwater rover simulator that can be used to detect oysters for this project. IMU and SONAR sensors are simulated mounted onto the rover. The simulator can be initialized with random landscapes, water turbidity, and with any underwater object randomly scattered in clusters. A custom rover path can be provided by user, which the rover will use to collect data and count oysters from and build the oyster map.

Generated underwater Scene

Camera, IMU and SONAR sensors integration

Segmentation for oyster detection

segmentation.mp4

Visual SLAM

vslam.mp4

Oyster Map Generation using SLAM and segmentation output

Tasks

• 2D bounding Box of objects from Blender 2.93
• Integrate IMU with blender
• Integrate LiDAR/SONAR with blender
• Train yolo on the generated data from blender
• Rover position data with detections on PCL

Google Colab Notebook

• colab notebook used to train the yolov4-tiny, find it here
• Modified the colab notebook provided here

Models

• We trained a yoloV4-tiny on a dataset of around 5000 images
• Download the model best weights file from here
• Copy the model weights in here

Blender model

• BlueROV model download from here
• Oysters model download from here

Oyster

• Real oyster shell 3D scanned download from here

• Real texture of the oysters download from here

• Synthetic oyster 3D model generated download from here

• Script and the necessary files for generating the Synthetic oyster shell 3D models download from here

• Dataset that we generated for the Synthetic Oysters download from here