Enlarge / The round lens of PrivacyLens captures standard digital video while the square lens senses heat. The heat sensor improves the camera's ability to spot and remove people from videos. (credit: Brenda Ahearn, Michigan Engineering)

Roombas can be both convenient and fun, particularly for cats who like to ride on top of the machines as they make their cleaning rounds. But the obstacle-avoidance cameras collect images of the environment—sometimes rather personal images, as was the case in 2020 when images of a young woman on the toilet captured by a Romba leaked to social media after being uploaded to a cloud server. It's a vexing problem in this very online digital age, in which Internet-connected cameras are used in a variety of home monitoring and health applications, as well as more public-facing applications like autonomous vehicles and security cameras.

University of Michigan (UM) engineers have been developing a possible solution: PrivacyLens, a new camera that can detect people in images based on body temperature and replace their likeness with a generic stick figure. They have filed a provisional patent for the device, described in a recent paper published in the Proceedings on Privacy Enhancing Technologies Symposium, held last month.

"Most consumers do not think about what happens to the data collected by their favorite smart home devices. In most cases, raw audio, images and videos are being streamed off these devices to the manufacturers' cloud-based servers, regardless of whether or not the data is actually needed for the end application," said co-author Alanson Sample. "A smart device that removes personally identifiable information (PII) before sensitive data is sent to private servers will be a far safer product than what we currently have."

Enlarge (credit: Witthaya Prasongsin)

Elon Musk, back in October 2021, tweeted that “humans drive with eyes and biological neural nets, so cameras and silicon neural nets are only way to achieve generalized solution to self-driving.” The problem with his logic has been that human eyes are way better than RGB cameras at detecting fast-moving objects and estimating distances. Our brains have also surpassed all artificial neural nets by a wide margin at general processing of visual inputs.

To bridge this gap, a team of scientists at the University of Zurich developed a new automotive object-detection system that brings digital camera performance that’s much closer to human eyes. “Unofficial sources say Tesla uses multiple Sony IMX490 cameras with 5.4-megapixel resolution that [capture] up to 45 frames per second, which translates to perceptual latency of 22 milliseconds. Comparing [these] cameras alone to our solution, we already see a 100-fold reduction in perceptual latency,” says Daniel Gehrig, a researcher at the University of Zurich and lead author of the study.

Replicating human vision

When a pedestrian suddenly jumps in front of your car, multiple things have to happen before a driver-assistance system initiates emergency braking. First, the pedestrian must be captured in images taken by a camera. The time this takes is called perceptual latency—it’s a delay between the existence of a visual stimuli and its appearance in the readout from a sensor. Then, the readout needs to get to a processing unit, which adds a network latency of around 4 milliseconds.