Lime has built its own camera-based sidewalk detection technology

Lime is finally bringing on some of its own city-appeasing technology. At a Lime event in Paris, the startup shared plans to pilot a computer vision platform that will use cameras to detect when users are riding on the sidewalk. The cities can either audibly alert the riders to their transgressions or slow them down.

In San Francisco and Chicago, Lime will be testing the technology on close to 400 scooters. The company held a demo of the new tech in Paris on Wednesday and hopes to expand its pilot to six cities by the end of the year.

It is easier for cities to blame micromobility companies and scooter riders for sidewalk riding, rather than invest the proper time and money in building protected bike lanes.

Bird and Superpedestrian use location-based systems to determine where scooters are parked. The computer vision tech of third party providers has been piloted by Voi, Spin and Zip. Lime has piloted third party computer vision systems to test the viability of the business model before investing in its own system. It isn't the first company to integrate such a system into a scooter Segway, a company that supplies many micro mobility companies, recently announced its own scooter.

There are two scooter ARAS camps that have their champion. The advocates say that their tech is cheaper and easier to use than computer vision tech. Adding a hardware element that may break or be vandalized on the streets is expensive.

According to Joe Kraus, president of Lime, the company is taking a long-term bet by investing in computer vision, which he thinks will be cheaper than augmentedGPS in the long run.

Kraus thinks about where massive money is being invested in order to bring things down the cost curve. The accuracy of image classification and detection is huge because of the amount of investment that is going into making camera based systems. There is a huge amount of investment going into the open source software side as well as on the chip side to make them cheaper and more efficient.

Getting hyper- accurate maps is important to improve scooter ARAS. Kraus doesn't think the same level of demand, investment and performance is happening for gps signaling

Kraus said that the cost of augmentation of the gps device is not cheap.

The executive argued that gps doesn't open up as many doors as it could. Lime has a plan to implement other use cases like parking detection. Lime and Bird are both using a rider's camera to determine if a scooter or e-bike is parked correctly.

Kraus said that Lime could use its computer vision tech for "broader localization efforts" or "non-repudiation in the case of accidents." Lime Vision can help Lime win brownie points with cities by sharing data on things like hotspots for sidewalk riding to help inform where to build bike lanes or the number of potholes.

The retrofittable, waterproof unit that affixes to the neck of the scooter below the handlebars is the first version of Lime Vision that will be tested. Kraus said that Lime's computer vision model can detect objects in less than a second. The scooter's brain is connected via a wire to the unit so it can communicate commands.

Kraus said that the second version of Lime's computer vision system would be integrated into the body of the vehicle.

Lime plans to pilot a new test to prevent drunk riding in 30 cities around the world. If riders don't hit the stop sign in a certain amount of time, they won't be able to ride.

Lime had tried out a feature that was activated after 10 p.m. It would ask riders if they agree that they are not drunk and fit to ride. Bird launched Safe Start, an in-app checkpoint that asked riders to enter a phrase into the app that it hoped would deter drunk people from riding.

Advanced rider assistance systems: Tech spawned by the politics of micromobility