Скачать или смотреть Scene Segmentation

#Scene_Segmentation


One of the most prevalent application of deep neural networks to self-driving is semantic segmentation, which associates image pixels with useful labels such as sign, light, curb, road, vehicle etc. The main use for segmentation is to identify the drivable surface, which aids in ground plane estimation, object detection and lane boundary assessment. Segmentation labels are also being directly integrated into object detection as pixel masks, for static objects such as signs, lights and lanes, and moving objects such cars, trucks, bicycles and pedestrians.

Why using generative models like Unet or Deeplabv3 is better than using simple object detection models like YOLO or SSD ?

As you can see, this is because it works at the pixel level instead of just surrounding the object with a bounding box, which naturally makes it more accurate.

You can find weights and training notebooks and the output videos in this repo : https://www.linkedin.com/posts/mohamed-whd...