The Foundation for the Promotion of Industrial Science

Fujitsu Corporation

The University of Tokyo

Fujitsu Microelectronics Limited

Masao Sakauchi

Shunsuke Kamijo

Katsushi Ikeuchi

Hiroshi Kawasaki

To track moving objects in a smaller number of temporarily stored time-series pictures, regarding N consecutive pictures (N&#x2267;2) within the time-series pictures, a method comprises the steps of: (a) by assigning the same ID to adjacent blocks if the absolute value of the difference between motion vectors of the blocks are less than a predetermined value, assigning different IDs to moving objects overlapping in a picture; (b) judging whether or not a first object of a first block group assigned a first ID and a second object of a second block group assigned a second ID are in contact with each other in each of the N consecutive pictures, and further each correlation between the first objects of temporally adjacent pictures in the N consecutive pictures is more than or equal to a predetermined value; and (c) tracking the first and second objects backward in time after the judgment at step (b) is positive.

Method and device for tracking moving objects in image

A feature amount of an inter-mobile unit relative movement are detected as an observation amount by an observation amount detecting section, time series of the observation amounts are stored as an observation series into a storage sectionto calculate a similarity of the observation series to a predetermined collision observation series by a classification section. A determination sectiondetermines to be a collision accident if, in a case where the similarity is larger than a predetermined value, a mobile unit associated with the similarity is at rest in a stoppage prohibition area set in a storage sectionand another mobile unit is moving, and to be a mobile unit failure if collision determination conditions except for the similarity are met. By consisting of not only a first scalar obtained by quantizing a relative velocity vector between mobile units but also a second scalar obtained by quantizing a relative position vector between mobile units as the observation amount, a relative movement between mobile units is classified in more detail. A mobile unit is tracked in units of block by a mobile unit tracking sectionto discriminate overlapped mobile units in pictures.

Method and apparatus for processing pictures of mobile object

An apparatus for generating an image includes a vehicle moving at a predetermined direction; and a plurality of cameras arranged on the vehicle along a linear line parallel to the predetermined direction and at different angles from each other with respect to the predetermined direction so as to include all areas of images to be acquired. The apparatus forms one image by integrating images at the same point acquired by the cameras, respectively without being synchronized the cameras with each other and using any external sensor.

Apparatus and method for generating image

By narrow region communication between a gate side communication apparatus (G-COM) and a mobile unit side communication apparatus (M-COM) passing through an on-road real gate at an interconnection, the G-COM assigns a real identification code (R-ID) IDincluding an intersection number to the M-COM after receiving a R-ID IDhaving been assigned from the M-COM, while time series pictures of the intersection including all real gates are taken by a camerainstalled to assign a virtual identification code (V-ID) to a mobile unit passing through a slit, corresponding to a real gate, in pictures by processing them. In response to the assignment of the R-ID, the R-ID is brought into correspondence with the V-ID. The mobile unit is tracked and when an anomalous behavior thereof is detected in pictures, warning information is transmitted to the M-COM using the corresponding R-ID. By gathering sets of IDand IDassociated with each other in a plurality of intersections, a mobile unit having displayed an anomalous behavior is tracked.

Mobile unit identification apparatus and method and apparatus for automatically warning to mobile unit

Each frame of time-series pictures shot by a camera is converted to a spatial differential frame picture by the following equations:()=&#x3a3;|()&#x2212;()|/(max/max),max/{exp(&#x2212;0.02(where &#x3a3; denotes a sum over di=&#x2212;1 to 1 and dj=&#x2212;1 to 1, Gi,j,max denotes the maximum pixel value of 3&#xd7;3 pixels having its center at the i-th row and j-th column, and Gmax denotes the assumable maximum value 255 of the pixel value G(i, j). Moving objects at a time t is discriminated based on a correlation between spatial differential frame pictures at times (t&#x2212;1) and t and a discrimination result of moving objects included in the spatial differential frame picture at the time (t&#x2212;1).

Growing community of inventors

Yokohama, Japan

Masao Sakauchi