KAIST researchers revealed that crowdsourced traffic violation reporting with smartphone-based continuous video capturing can dramatically change the current practice of policing activities on the road and will significantly improve traffic safety.
Professor Uichin Lee of the Department of Industrial and Systems Engineering and the Graduate School of Knowledge Service Engineering at KAIST and his research team designed and evaluated Mobile Roadwatch, a mobile app that helps citizen record traffic violation with their smartphones and report the recorded videos to the police.
This app supports continuous video recording just like onboard vehicle dashboard cameras. Mobile Roadwatch allows drivers to safely capture traffic violations by simply touching a smartphone screen while driving. The captured videos are automatically tagged with contextual information such as location and time. This information will be used as important evidence for the police to ticket the violators. All of the captured videos can be conveniently reviewed, allowing users to decide which events to report to the police.
The team conducted a two-week field study to understand how drivers use Mobile Roadwatch. They found that the drivers tended to capture all traffic risks regardless of the level of their involvement and the seriousness of the traffic risks. However, when it came to actual reporting, they tended to report only serious traffic violations, which could have led to car accidents, such as traffic signal violations and illegal U-turns. After receiving feedback about their reports from the police, drivers typically felt very good about their contributions to traffic safety.
At the same time, some drivers felt pleased to know that the offenders received tickets since they thought these offenders deserved to be ticketed. While participating in the Mobile Roadwatch campaign, drivers reported that they tried to drive as safely as possible and abide by traffic laws. This was because they wanted to be as fair as possible so that they could capture others’ violations without feeling guilty. They were also afraid that other drivers might capture their violations.
Professor Lee said, “Our study participants answered that Mobile Roadwatch served as a very useful tool for reporting traffic violations, and they were highly satisfied with its features. Beyond simple reporting, our tool can be extended to support online communities, which help people actively discuss various local safety issues and work with the police and local authorities to solve these safety issues.”
Korea and India were the early adaptors supporting video-based reporting of traffic violations to the police. In recent years, the number of reports has dramatically increased. For example, Korea’s ‘Looking for a Witness’ (released in April 2015) received more than half million reported violations as of November 2016. In the US, authorities started tapping into smartphone recordings by releasing video-based reporting apps such as ICE Blackbox and Mobile Justice. Professor Lee said that the existing services cannot be used while driving, because none of the existing services support continuous video recording and safe event capturing behind the wheel.
Professor Lee’s team has been incorporating advanced computer vision techniques into Mobile Roadwatch for automatically capturing traffic violations and safety risks, including potholes and obstacles. The researchers will present their results in May at the ACM CHI Conference on Human Factors in Computing Systems (CHI 2017) in Denver, CO, USA. Their research was supported by the KAIST-KUSTAR fund.
(Caption: A driver is trying to capture an event by touching a screen. The Mobile Radwatch supports continuous video recording and safe event captureing behind the wheel.)
Professor Dongsu Han from the School of Electrical Engineering has been appointed as the program chair for the 16th Association for Computing Machinery’s International Conference on emerging Networking EXperiments and Technologies (ACM CoNEXT 2020). Professor Han is the first program chair to be appointed from an Asian institution. ACM CoNEXT is hosted by ACM SIGCOMM, ACM's Special Interest Group on Data Communications, which specializes in the field of communication and computer networ2020-06-02
(from left: MS candidate Anish Byanjankar, Research Assistant Professor Hyosu Kim and Professor Insik Shin) Time passes so quickly, especially in the morning. Your hands are so busy brushing your teeth and checking the weather on your smartphone. You might wish that your mirror could turn into a touch screen and free up your hands. That wish can be achieved very soon. A KAIST team has developed a smartphone-based touch sound localization technology to facilitate ubiquitous interact2018-12-26
People often use their hands when describing an object, while pens are great tools for describing objects in detail. Taking this idea, a KAIST team introduced a new 3D sketching workflow, combining the strengths of hand and pen input. This technique will ease the way for ideation in three dimensions, leading to efficient product design in terms of time and cost. For a designer's drawing to become a product in reality, one has to transform a designer's 2D drawing into a 3D shape; however2018-07-25
Pressing a button appears effortless. People easily dismisses how challenging it is. Researchers at KAIST and Aalto University in Finland, created detailed simulations of button-pressing with the goal of producing human-like presses. The researchers argue that the key capability of the brain is a probabilistic model. The brain learns a model that allows it to predict a suitable motor command for a button. If a press fails, it can pick a very good alternat2018-03-22
Sangeun Oh, a Ph.D. candidate in the School of Computing was selected as a Google PhD Fellow in 2017. He is one of 47 awardees of the Google PhD Fellowship in the world. The Google PhD Fellowship awards students showing outstanding performance in the field of computer science and related research. Since being established in 2009, the program has provided various benefits, including scholarships worth $10,000 USD and one-to-one research discussion with mentors from Google. His resear2017-09-27