Problem Statement - The challenge is to develop a real-time object detection model for autonomous vehicles using computer vision techniques and Intel® AI Analytics Toolkits its libraries, and SYCL/DPC++ Libraries.
Team Leader Email - [email protected]
Datasets drive vision progress, yet existing driving datasets are limited in terms of visual content, scene variation, the richness of annotations, and the geographic distribution and supported tasks to study multitask learning for autonomous driving the images for "other vehicle", "pedestrian", "traffic light", "traffic sign", "truck", "train", "other person", "bus", "car", "rider", "motorcycle", "bicycle", "trailer” can be used for training. Goal is to detect and classify traffic objects in a video in real-time using two approaches. We can train the two state-of-the-art models YOLO and Faster R-CNN on the Berkeley DeepDrive dataset to compare their performances and achieve a comparable mAP to the current state.
Model zoo Intel architecture pre trained models from oneApi Ai Analytics Toolkit used here for computer vision. YOLOv4 Algorithm python openCV python numpy ##intel oneDNN toolkit
- pip install openCV
- pip install numpy
- cd oneDNN
- mkdir build && cd build
- !cmake /content/oneDNN
- !make -j$(nproc)
- pip install onednn-cpu-gomp
- pip install onednn-cpu-tbb
Learnt about AI ML and technologies used here which is most beneficial now, and also learned how to improve previous versions.