Every densely populated has a problem: traffic congestion. In China, especially, the rapid increase in the rate of car ownership has intensified security and safety problems, such as traffic violations and fatal accidents.

As a result, in recent years there are high expectations that initiatives involving remote, centralised management of large-scale urban deployments of surveillance cameras can be used for objectives such as improved traffic safety, reduced pollution and reduced congestion.

However, when monitoring surveillance cameras installed over a large area calls, it is important to quickly and correctly extract the information needed from a huge volume of imagery, and convey that to the relevant people. The issue with traffic-monitoring technologies that use conventional image recognition is that they are highly susceptible to the influence of a variety of environmental factors such as light sources, including headlights, sunlight, and shadows. Currently, there are limits to how much recognition accuracy could be improved when using existing cameras for analysis using video recognition. This is because it is difficult to adjust the cameras, their position and direction in accordance with constantly changing environmental variations. In addition, it's also difficult to efficiently and accurately recognise such varied and complex incidents as traffic accidents and violations.

To address this, Fujitsu Laboratories and Fujitsu Research and Development Centre have developed what they described as a highly accurate vehicle-recognition technology that tolerates changes in the surrounding environment, including changes in light, time of day and fog, and another technology for efficiently identifying complex incidents, such as traffic accidents.

The technology makes use of image processing and machine-learning to analyse surveillance camera images of traffic, with high accuracy and in real time, to recognise traffic conditions such as congestion and accidents, as well as violations.

Fujitsu traffic analysis cr Figure 1: Sample incidents recognised through image analysis (Source: Fujitsu)

According to Fujitsu, the technology achieves high-precision traffic-video analysis by combining two technologies. The first is a technology that analyses the images from surveillance cameras installed along highways and streets, automatically grouping characteristics that can lead to recognition errors, such as changes in lighting and environmental factors including night and fog, and images from cameras that have been similarly positioned. This leads to efficient machine learning, increasing recognition accuracy.

The second is a technology that analyses moving objects, such as vehicles and people, and efficiently identifies complex incidents such as accidents, while minimising computational demands.

In field trials of this technology conducted in cities around China in collaboration with the Tsingha University Suzhou Automobile Research Institute (TSARI), it was found that 11 types of incidents of interest, such as traffic accidents and violations, were recognized with accuracy levels of 90-95%. Even when used with existing cameras that do not have advanced image-correction features, Fujitsu's technology can be used to deliver a highly accurate, low-cost monitoring system that can automatically assess traffic conditions, apply traffic-flow controls and analysis to reduce congestion, and take quick action in response to accidents and traffic violations.

Fujitsu Laboratories and Fujitsu Research and Development Centre are working to increase the accuracy and incidents recognisable with this technology, and plan to continue field trials jointly with TSARI. Also, by combining this technology with FUJITSU Intelligent Society Solution SPATIOWL, Fujitsu Limited's cloud service that utilises location information, after fiscal 2016 the companies aim to roll out a service in China that recognises incidents occurring over a wide area in real time. Following that, they aim to extend to other regions, including Japan.