This project essentially converts a neural network based desktop pothole detector above (fp32 aka single precision floating point/32 bits), to jetson nano neural network based pothole detector (fp16 half precision floating point 16 bits). (Purpose of which is to add the jetson nano with the trained half precision pothole detector to my car, and perhaps offer to others for sale?)
Would you buy a smart pothole detector for your vehicle?
########################################################
########################################################
#####Test on image sample 0, with 1 potholes
getPrediction ('pothole_sample_0.jpg')
#####Test on image sample 1, with 3 potholes
getPrediction ('pothole_sample_1.jpg')
#####Test on image sample 2, with 8 potholes
getPrediction ('pothole_sample_2.jpg')
#####Test on image sample 3, with 0 potholes
getPrediction ('pothole_negative_sample.jpg')
Github + code:
https://github.com/JordanMicahBennett/Smart-Ai-Pothole-Detector------Powered-by-Tensorflow-TensorRT-on-Google-Colab-and-or-Jetson-Nano
Future work:
- Night-time ai pothole detection. (Maybe give pothole detector brightened images as input)
- Live speedbump detection. (Especially those haphazzardly painted ones that are painted black like road)
- Other obstacle detection, that may be to thin for car sensors to pick up.