Is it possible that I use camera for taking the images and apply object classifiers and detection method like yolo and faster rcnn for object detection and then apply reinforcement learning algorithm for autonomous navigation? Does this approach helps me to navigate fast or not?
Yes sure. however, you should carefully choose the object recognition method you are going to use.
Faster R-CNNs are likely the most “heard of” method for object detection using deep learning; however, the technique can be difficult to understand (especially for beginners in deep learning), hard to implement, and challenging to train.
furthermore, the algorithm can be quite slow, on the order of 7 FPS which is not suitable in your case.
On the other hand, YOLO is much faster, capable of processing 40-90 FPS on a Titan X GPU. The super fast variant of YOLO can even get up to 155 FPS.
The problem with YOLO is that it leaves much accuracy to be desired.
One good option to be considered is the combination of mobileNets and SSD detector.
Great question ... if you got the answer please forward it to me.
Since they maintain a high computational cost, I do not know if they are appropiate for real-time
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Control Theory
- Control Systems