Canon Kabushiki Kaisha

Masahiro Matsushita

Hirotaka Shiiyama

Koichi Magai

Hidetomo Sohma

Hideki Sorakado

Hiroshi Tojo

Kotaro Yano

Tomomi Takata

Yaohai Huang

Kazuyo Ikeda

Cheng Tan

Rongjun Li

Sen Na

This invention prevents a collation database from becoming bulky and shortening the delay time needed from person detection to registration in the collation database. An information processing apparatus comprises an acquiring unit which acquires a video, a detecting unit which detects a whole body or a part of a person from at least one frame of the acquired video, a tracking unit which tracks the whole body or the part of the person detected, and a registering unit which registers, in a database, a feature amount extracted from the whole body or the part of the person tracked during a first period from a timing of a start of tracking of the whole body or the part of the person by the tracking unit to a timing before an end of the tracking by the tracking unit.

Information processing apparatus, method of controlling the same, and storage medium

An information processing apparatus includes first and second acquisition units and first and second search units. The first acquisition unit acquires a first feature amount from a search source image including a search object. The first search unit searches for the search object from a plurality of video images based on the first feature amount acquired by the first acquisition unit. The second acquisition unit acquires a second feature amount from the search object searched by the first search unit. The second feature amount is different from the first feature amount. The second search unit searches, based on the second feature amount acquired by the second acquisition unit, the search object from a video image, among the plurality of video images, in which the search object is not searched by at least the first search unit.

Information processing apparatus, information processing method, and storage medium

A first retriever performs, based on a person feature of a person extracted from a video image before an acceptance time point of a retrieval instruction of a target person and stored and a feature extracted from the target person related to the retrieval instruction, a first retrieving process of retrieving the target person from the video image stored, a second retriever performs, based on a feature of a person extracted from a video image after the acceptance time point and the feature of the target person extracted from a query image of the retrieval instruction, a second retrieving process of retrieving the target person from the video image input after the acceptance time point, and the first retriever performs the first retrieving process to the video image input during a period from the acceptance time point to preparation completion of the second retrieving process and second retrieving process start.

One or more embodiments relate to an object indexing method, object indexing device and object indexing system. An object indexing method may include an initializing step of dividing at least one first data container and at least one second data container, and initializing respectively the first and the second data containers by using a first data indexer and a second data indexer; a first indexing step of adding the input feature vector of a specific object into a first data container currently being filled by using the first data indexer; and a second indexing step, when the data size in the first data container being filled has reached a threshold, selecting another first data container as the first data container currently being filled, and in the case of executing the first indexing step, converting bulk data in the first data container previously being filled into one available second data container.

Object indexing method, object searching method, and object indexing system

When searching for a registered image similar to a query image, an image processing apparatus estimates an area having a difference by comparing images determined to be similar if a plurality of similar images is found at the time of search of a similar image using an image feature amount in order to enhance search accuracy. Then, the image processing apparatus compares the query image with the plurality of images similar to the query image based on the difference area.

Image processing apparatus, image processing method, and storage medium

An image processing apparatus includes a detection unit configured to detect at least one identical object or at least one object of an identical type from images captured by a plurality of imaging apparatuses, a selection unit configured to select at least one object from among at least one detected object based on color information of each object, and a determination unit configured to determine color correction information related to a plurality of the imaging apparatuses based on color information of at least one selected object. The image processing apparatus enables restricting the degradation of the color matching accuracy.

Image processing apparatus, image processing method, and recording medium

The present invention suppresses feature amounts of faces to be registered in a collation database, thereby preventing the collation database from being bloated. An information processing apparatus of the present invention includes an acquisition unit configured to acquire a video, a detection unit configured to detect at least one face of the same person from a plurality of frames of the acquired video, a classification unit configured to classify the detected faces into a plurality of predetermined groups, a selection unit configured to select, from the faces classified into the groups, not more than a first predetermined number of faces for each group, wherein the first predetermined number is an integer of not less than 2, and a registration unit configured to register feature amounts of the selected faces in a database.

Information processing apparatus for registration of facial features in a collation database and control method of the same

There is provided with an image processing apparatus. An evaluation is set for each of the pairs. The evaluation is set based on at least one of the number of feature points in the first image where local feature amounts are similar to a local feature amount at one of the pair or the number of feature points in the second image where local feature amounts are similar to a local feature amount at one of the pair, in such a manner that the smaller the number of feature points, the higher the evaluation. A similarity between the first image and the second image is determined using a RANSAC method. A pair having a high evaluation is used with priority in derivation of a function for transforming coordinates using the RANSAC method.

A tint of an object according to a second image capturing device is corrected by a first parameter for correcting a tint of a second object that the second image capturing device captured in a first time zone to a tint of a first object that a first image capturing device captured in a first time zone. If a third object captured by a third image capturing device corresponds to the first object, a parameter for correcting a tint of the third object to the tint of the first object is used for correcting a tint of an object according to a third image capturing device. If the third object corresponds to the second object, the first parameter and a third parameter for correcting the tint of the third object to the tint of the second object is used for the foregoing tint correction.

Image processing apparatus, image processing method, and non-transitory computer-readable storage medium

A feature point is extracted from an input image including an image region for which depth values of pixels change consecutively. A transformation that normalizes depth values of pixels of a vicinity of the feature point with respect to a region of at least a portion of the input image is set as a normalization transformation, and an image for a feature amount calculation is generated by performing the normalization transformation on a pixel position of the feature point. A feature amount is calculated from the image for the feature amount calculation.

Depth normalization transformation of pixels

This invention suppresses bloating of indices for an image search. To accomplish this, when a target image to be registered is given, an apparatus described in this specification executes partial image search processing using the target image to be registered as a query image. As a result, if a corresponding image is found, and an already registered image includes the query image, the target image to be registered is registered as an image linked to the already registered image.

Image search apparatus and control method thereof

To make it easier to grasp characters that appear across different images by determining a pair of character area images to be a combination target based on a degree of similarity or a position of each character area image extracted from different images, and connecting and combining overlapping area images that are the determined pair of character area images and that have a similar image feature amount.

Image processing apparatus, image processing method, and program

An image processing apparatus executes smoothing processing (reduction conversion) of an input image to acquire a smoothed image (reduced image), acquires a normalization parameter for normalization from the smoothed image, and normalizes pixel values of the input image based on the normalization parameter.

Growing community of inventors

Yokohama, Japan

Masahiro Matsushita