Bengaluru engineer develops AI app to detect potholes, identify responsible contractors


Daijiworld Media Network - Bengaluru

Bengaluru, Aug 18: For most commuters, a pothole means a bumpy ride, potential vehicle damage, and yet another civic complaint. However, a Bengaluru-based engineer has transformed this everyday headache into a data-driven solution by developing a unique AI-powered app that not only spots potholes but also identifies the contractor responsible for fixing them.

Gaurav Sen, the engineer behind the innovation, recently demonstrated his system in a video shared on Instagram in collaboration with ChatGPT India. The video later went viral on X (formerly Twitter), garnering widespread attention and praise.

The system designed by Sen utilises a dashcam, a GPS, and an accelerometer fitted in his car to collect real-time information as he drives. The captured footage is then processed using AI vision models to accurately identify potholes of various sizes. Notably, the system is advanced enough to detect potholes that are difficult to spot from a distance or those that closely resemble speed breakers.

According to Sen, he used Codex to build the app, which records the relevant data and transmits it to OpenAI.

Going a step beyond mere detection, Sen designed the app to answer the most crucial question: who is accountable for the repair? To achieve this, he modified the application to scan through 2,900 government contracts, enabling it to pinpoint the exact contractor responsible for a particular stretch of road. He explained that this feature is especially beneficial when a road is still under its warranty period, as the contractor is obligated to repair any defects without levying additional costs on the government.

The highly efficient app can generate a structured record within just four seconds. This comprehensive output includes a photograph of the pothole, its exact geographic location, the tender number, and the details of the officer responsible for that specific road.

During a real-world test on his daily commute to work, Sen's system successfully detected 12 potholes along the route, providing him with documented evidence that can be directly used to raise formal complaints with civic authorities.

The innovative concept has resonated well beyond Bengaluru. Following the video's popularity on X, netizens lauded Sen for developing a practical solution to a problem that plagues motorists nationwide. Many users also suggested that civic authorities and municipal corporations should adopt a similar AI-driven system to identify damaged roads and expedite repair works.

 

 Watch Video:

 


 

 

 

  

Top Stories


Leave a Comment

Title: Bengaluru engineer develops AI app to detect potholes, identify responsible contractors



You have 2000 characters left.

Disclaimer:

Please write your correct name and email address. Kindly do not post any personal, abusive, defamatory, infringing, obscene, indecent, discriminatory or unlawful or similar comments. Daijiworld.com will not be responsible for any defamatory message posted under this article.

Please note that sending false messages to insult, defame, intimidate, mislead or deceive people or to intentionally cause public disorder is punishable under law. It is obligatory on Daijiworld to provide the IP address and other details of senders of such comments, to the authority concerned upon request.

Hence, sending offensive comments using daijiworld will be purely at your own risk, and in no way will Daijiworld.com be held responsible.