Abstract: A monitoring device has a detection target person storage part in which a feature of a face of each detection target person is stored, an image processor that processes images captured with a plurality of imaging devices having different imaging areas, and detects the image in which the detection target person stored in the detection target person storage part is captured, a detection information storage part in which detection information is stored, the detection information including the detection target person, imaging area, and imaging date and time with respect to the image in which the detection target person detected by the image processor is captured, and a reliability calculator that calculates a degree of detection reliability in the image processor based on a time-space rationality, the time-space rationality being determined from a plurality of pieces of detection information on each detection target person.

Abstract: The present invention relates to a tracking method and a tracking device adopting multiple observation models with different life spans. The tracking method is suitable for tracking an object in a low frame rate video or with abrupt motion, and uses three observation models with different life spans to track and detect a specific subject in frame images of a video sequence. An observation model I performs online learning with one frame image prior to the current image, an observation model II performs online learning with five frames prior to the current image, and an observation model III is offline trained. The three observation models are combined by a cascade particle filter so that the specific subject in the low frame rate video or the object with abrupt motion can be tracked quickly and accurately.

Abstract: A monitoring device has a detection target person storage part in which a feature of a face of each detection target person is stored, an image processor that processes images captured with a plurality of imaging devices having different imaging areas, and detects the image in which the detection target person stored in the detection target person storage part is captured, a detection information storage part in which detection information is stored, the detection information including the detection target person, imaging area, and imaging date and time with respect to the image in which the detection target person detected by the image processor is captured, and a reliability calculator that calculates a degree of detection reliability in the image processor based on a time-space rationality, the time-space rationality being determined from a plurality of pieces of detection information on each detection target person.

Abstract: The present invention discloses an object detection apparatus and method. A feature extracting section of the present invention comprises: a feature point extracting section, for extracting a combination of predetermined feature point pairs from an image; a pixel value obtaining section, for obtaining a pixel value of each feature point in the combination of feature point pairs; a feature point comparing section, for comparing, in accordance with the pixel values obtained by the pixel value obtaining section, two feature points in each feature point pair to obtain a logical value; and an feature obtaining section, for determining the feature of the image in accordance with the logical value.

Abstract: The invention discloses a detecting device for specific subjects and a learning device and method thereof. The detecting device for specific subjects includes an input unit, one or more strong classifying units, a storage unit and a judging unit, wherein the input unit is used for inputting images to be detected; the strong classifying units are used for carrying out strong classification to the image, each strong classifying unit includes one or more weak classifying units, and the weak classifying unit carries out weak classification to the image with a weak classifying template; the storage unit stores the weak classifying template used by the weak classifying unit; and the judging unit judges whether or not the image contains specific subjects according to the classification result of the strong classifying unit.

Abstract: A method for tracking objects includes identifying a target, identifying a plurality of auxiliary objects related to the target, and tracking the target using the plurality of auxiliary objects.

Abstract: An apparatus and a method for detecting from an image a particular subject corresponding to multiple views of the subject by dividing a particular subject space into a plurality of subject subspaces and further dividing a subject subspace into subject subspaces representing multiple views; configuring a tree-structured detector wherein the tree structure has a root node that covers all subject subspaces and has a plurality of branches, each branch corresponding to a child node that covers at least one subject subspace; training each node to determine which nodes in the adjacent lower layer the images of the subject in the corresponding nodes should be sent.

Abstract: The present invention discloses an object detection apparatus and method. A feature extracting section of the present invention comprises: a feature point extracting section, for extracting a combination of predetermined feature point pairs from an image; a pixel value obtaining section, for obtaining a pixel value of each feature point in the combination of feature point pairs; a feature point comparing section, for comparing, in accordance with the pixel values obtained by the pixel value obtaining section, two feature points in each feature point pair to obtain a logical value; and an feature obtaining section, for determining the feature of the image in accordance with the logical value.

Abstract: The invention discloses a detecting device for specific subjects and a learning device and method thereof. The detecting device for specific subjects includes an input unit, one or more strong classifying units, a storage unit and a judging unit, wherein the input unit is used for inputting images to be detected; the strong classifying units are used for carrying out strong classification to the image, each strong classifying unit includes one or more weak classifying units, and the weak classifying unit carries out weak classification to the image with a weak classifying template; the storage unit stores the weak classifying template used by the weak classifying unit; and the judging unit judges whether or not the image contains specific subjects according to the classification result of the strong classifying unit.

Abstract: The present invention relates to a tracking method and a tracking device adopting multiple observation models with different life spans. The tracking method is suitable for tracking an object in a low frame rate video or with abrupt motion, and uses three observation models with different life spans to track and detect a specific subject in frame images of a video sequence. An observation model I performs online learning with one frame image prior to the current image, an observation model II performs online learning with five frames prior to the current image, and an observation model III is offline trained. The three observation models are combined by a cascade particle filter so that the specific subject in the low frame rate video or the object with abrupt motion can be tracked quickly and accurately.

Abstract: Method and apparatus for face alignment by building a hierarchical classifier network. The hierarchical classifier network connects the tasks of face detection and face alignment into a smooth coarse-to-fine procedure. Texture classifiers are trained to recognize feature texture at different scales for different resolution layers. A multi-layer structure is employed to organize the texture classifiers, which begins with one classifier at the first layer and gradually refines the localization of feature points using additional texture classifiers in subsequent layers.

Abstract: Unlike in the prior art in which the correspondence between a feature and a judgment value in an intended area is obtained by a single threshold value, the correspondence of the judgment value is obtained independently for each feature by use of a look-up table or the like. This makes it possible to achieve an accurate correspondence between the judgment value and the feature and thus to improve the high processing accuracy. Also, in the prior art, the judgment is repeated several times to secure the accuracy of the judgment and based on the total result thereof, the final judgment is made. Since the accuracy of each process is improved, however, the number of times the judgment is repeated is reduced for a higher processing speed.

Abstract: Method and apparatus for face alignment by building a hierarchical classifier network. The hierarchical classifier network connects the tasks of face detection and face alignment into a smooth coarse-to-fine procedure. Texture classifiers are trained to recognize feature texture at different scales for different resolution layers. A multi-layer structure is employed to organize the texture classifiers, which begins with one classifier at the first layer and gradually refines the localization of feature points using additional texture classifiers in subsequent layers.

Abstract: A method for tracking objects includes identifying a target, identifying a plurality of auxiliary objects related to the target, and tracking the target using the plurality of auxiliary objects.

Abstract: An apparatus and a method for detecting from an image a particular subject corresponding to multiple views of the subject by dividing a particular subject space into a plurality of subject subspaces and further dividing a subject subspace into subject subspaces representing multiple views; configuring a tree-structured detector wherein the tree structure has a root node that covers all subject subspaces and has a plurality of branches, each branch corresponding to a child node that covers at least one subject subspace; training each node to determine which nodes in the adjacent lower layer the images of the subject in the corresponding nodes should be sent.

Abstract: Unlike in the prior art in which the correspondence between a feature and a judgment value in an intended area is obtained by a single threshold value, the correspondence of the judgment value is obtained independently for each feature by use of a look-up table or the like. This makes it possible to achieve an accurate correspondence between the judgment value and the feature and thus to improve the high processing accuracy. Also, in the prior art, the judgment is repeated several times to secure the accuracy of the judgment and based on the total result thereof, the final judgment is made. Since the accuracy of each process is improved, however, the number of times the judgment is repeated is reduced for a higher processing speed.

Abstract: An image editing apparatus, an image editing method and a program therefor are disclosed, in which an image of each object is corrected in accordance with the race, sex and age and individual preferences. A CPU 4 retrieves an image to be processed, from a scanner 2 or a memory card reader 3 and detects a face image from the retrieved image. Further, the CPU 4 infers the race, age and sex of the object using the feature amounts of the detected face image, sets correction parameters suitable for the inference result, and adjusts the skin color of the face image and otherwise corrects the face image against back light. The corrected image is output to a printer 11 and printed as a photo.

Abstract: An image pickup device, an image pickup device program and an image pickup method are disclosed, in which an image is picked up by setting the image pickup conditions suitable for an object, and the face image thus picked up can be easily corrected in accordance with the characteristics and preferences of the object. Once a shutter button is pressed halfway and a line-of-sight sensor 14 confirms that the line of sight of a photographer is set, a CPU 5 generates a preview image, and upon detection of the face image, infers the race, age and sex of the object using the feature amount of the face image. Further, image pickup parameters suitable for the inference result and the measurement of a length measuring sensor 13 are set, and the main image pickup process is executed under the image pickup conditions corresponding to the parameters.