China’s BYD Works on AI to Detect Animals Under Cars | eWeek

China’s BYD Works on AI to Detect Animals Under Cars

A white cat with heterochromia hiding underneath a car.

Source: Rana Kaname/Unsplash

Écrit par
Liz Ticong
Liz Ticong
Jun 29, 2026
3 minute read
eWeek Le contenu et les recommandations de produits sont indépendants de la rédaction. Nous pouvons gagner de l'argent lorsque vous cliquez sur des liens vers nos partenaires. En savoir plus

Most drivers check their mirrors before pulling away. Few check under the car.

China’s BYD is working on an AI system that could warn drivers if an animal or other living being is beneath a parked vehicle. The technology is still at the patent stage, but it shows how the automaker is pushing vehicle safety beyond lane alerts and parking cameras.

A small under-car blind spot can become a real safety risk, especially in places where cats, dogs, or strays seek warmth or shade beneath parked vehicles.

How the system works

According to ITHome, the AI system starts by taking a picture of the car’s lower area after the vehicle is powered off. That image becomes a reference point, almost like a “before” photo.

Before the vehicle moves again, a new real-time image is compared with the stored reference. Any area that looks different is flagged for a closer look.

The comparison helps the software avoid treating every shadow, dirt patch, leaf, or piece of road debris as a new concern. By narrowing the search to areas that changed, the system can focus on what may have appeared after the car was parked.

Once a changed area is detected, the software analyzes that spot to determine whether it could be a living being, such as an animal or a person, or ordinary road clutter.

BYD is also looking inside the car

BYD is applying the same safety thinking to the cabin.

ITHome reported that the company also announced an earlier patent for detecting occupants left inside a vehicle. Instead of cameras, the cabin system uses radar signals to check whether someone remains in the car.

One system watches the area around the vehicle through imaging and computer vision. Another checks the cabin through radar-based sensing.

Both patents point to the same product direction: vehicles that use different sensors for different safety problems, from cameras outside the car to radar inside the cabin.

China’s smart cars are competing on more than range

China’s EV market is already crowded with cars that use AI and software to feel more responsive to drivers. 

At Auto China 2026 in Beijing, Xpeng said its latest AI model can respond to commands such as “park near the entrance to the shopping centre,” while Xiaomi showed an AI-powered operating system that can detect when drivers appear stressed and adjust lighting and music, The Guardian reported.

BYD’s patents take that idea in a more safety-focused direction. Instead of asking what a car can do for comfort or convenience, the company is looking at whether sensors can catch the moments people miss, such as a stray sleeping peacefully near a parked car or a child left inside during a busy day, early enough to prevent an accident or save a life.

Advertisement

The real challenge for drivers and automakers

If BYD’s under-car detection feature reaches production, the real question will be whether drivers trust it enough to act.

An alert only helps if it feels accurate. Frequent false alarms could lead drivers to dismiss the warning, while missed detections could undermine confidence in the feature.

Automakers would also have to decide how the alert should appear. A small dashboard icon may be easy to miss. On the other hand, a louder warning could frustrate drivers if it appears too often.

Future car safety may depend as much on driver response as detection. Spotting a risk is only one part of the challenge; getting someone to notice the alert and respond in time will decide whether features like this work in daily use. 

Related reading: A Chinese cybersecurity firm says its new AI tool rivals Anthropic’s Mythos, but outside validation is still unclear.

Liz Ticong

Liz Ticong is a staff writer for eWeek and TechRepublic focused on AI, cybersecurity, enterprise software, and data. She has more than 10 years of editorial experience as a technology industry writer, combining reporting, product research, and hands-on software testing in her coverage. Her work has been published on Datamation, Enterprise Networking Planet, and TechnologyAdvice.com. She writes technology news, software reviews, product comparisons, and buyer’s guides for business and IT readers.

eWeek Logo

eWeek has the latest technology news and analysis, buying guides, and product reviews for IT professionals and technology buyers. The site's focus is on innovative solutions and covering in-depth technical content. eWeek stays on the cutting edge of technology news and IT trends through interviews and expert analysis. Gain insight from top innovators and thought leaders in the fields of IT, business, enterprise software, startups, and more.

Propriété de TechnologyAdvice. © 2026 TechnologyAdvice. Tous droits réservés

Divulgation publicitaire : Certains des produits qui apparaissent sur ce site proviennent d'entreprises dont TechnologyAdvice reçoit une compensation. Cette compensation peut influencer la façon dont les produits apparaissent sur ce site, notamment l'ordre dans lequel ils apparaissent. TechnologyAdvice n'inclut pas toutes les entreprises ou tous les types de produits disponibles sur le marché.