541 results about "Object detector" patented technology

An object detection system for detecting instances of an object in a digital image includes an image integrator and an object detector, which includes a classifier (classification function) and image scanner. The image integrator receives an input image and calculates an integral image representation of the input image. The image scanner scans the image in same sized subwindows. The object detector uses a cascade of homogenous classification functions or classifiers to classify the subwindows as to whether each subwindow is likely to contain an instance of the object. Each classifier evaluates one or more features of the object to determine the presence of such features in a subwindow that would indicate the likelihood of an instance of the object in the subwindow.

Presented are systems and methods that provide a unified end-to-end detection pipeline for object detection that achieves impressive performance in detecting very small and highly overlapped objects in face and car images. Various embodiments of the present disclosure provide for an accurate and efficient one-stage FCN-based object detector that may be optimized end-to-end during training. Certain embodiments train the object detector on a single scale using jitter-augmentation integrated landmark localization information through joint multi-task learning to improve the performance and accuracy of end-to-end object detection. Various embodiments apply hard negative mining techniques during training to bootstrap detection performance. The presented are systems and methods are highly suitable for situations where region proposal generation methods may fail, and they outperform many existing sliding window fashion FCN detection frameworks when detecting objects at small scales and under heavy occlusion conditions.

In various examples, detected object data representative of locations of detected objects in a field of view may be determined. One or more clusters of the detected objects may be generated based at least in part on the locations and features of the cluster may be determined for use as inputs to a machine learning model(s). A confidence score, computed by the machine learning model(s) based at least in part on the inputs, may be received, where the confidence score may be representative of a probability that the cluster corresponds to an object depicted at least partially in the field of view. Further examples provide approaches for determining ground truth data for training object detectors, such as for determining coverage values for ground truth objects using associated shapes, and for determining soft coverage values for ground truth objects.

A system and method associate each of a plurality of computer applications with a corresponding physical location external to the computer and display a given one of the applications when the user focuses attention on the physical location associated with that application. Preferably the display as a view window in a graphical user interface, and the user has means for moving that window relative to the given application. The computer can be a portable and display device can be head mounted. Preferably an input device enables the user to interact with the given application, and preferably the physical locations bring to mind their associated applications. In some embodiments, an identifier, such as a bar code or a coded transmitter, is placed near each of the physical locations to help detect when the user focuses attention on that particular location. The invention also provides a head mounted unit which projects a visual image to the user wearing it. The unit also includes an object detector for generating a signal when pointed at certain objects. The object detector is mounted so a user wearing the unit can point the detector by moving his or her head. Preferably the unit includes a see through window so the user can see his or her physical surroundings. The invention also provides for a computer which includes a display, a device for generating a display object on the display, such as a cursor, and a motion sensor for causing the display object to move within the display in response to motion of the display.

An image cropping system utilizes memory, an object detector, and an image cropper. A set of digital data that defines a graphical image is stored in the memory. The object detector analyzes the set of digital data and automatically identifies a portion of the digital data that defines an image of a particular object. The image cropper then uses the identified portion to determine a position of the object image within the graphical image. Based on the position of the object image within the graphical image, the image cropper automatically crops the digital data. In this regard, the position of the object image within the graphical image serves as a reference for determining which portions of the set of digital data should be cropped.

Registration correction for optical tomographic imaging in three dimensions. An object of interest is illuminated to produce an image. A lateral offset correction value is determined for the image. An axial offset correction value is determined for the image. The lateral offset correction value and the axial offset correction value are applied to the image to produce a corrected file image.

An object detector, an object detecting method and a robot can reduce diction errors of detecting wrong objects without increasing the volume of the computational operation to be performed to detect the right object. A face detector 101 comprises a face detecting section 110 that operates like a conventional face detecting section and is adapted to roughly select face candidates from an input image by template matching and detect face candidates by means of a support vector machine for face recognition, a non-face judging section 120 that detects non-face candidates that are judged to be non-faces and removes them from the face candidates selected by the face detecting section 110 and a skin tracker section 114 for tracking a face region after the non-face judgment. When the assumed distance between the face detector and the face as computed from the input image and the measured distance as measured by a distance sensor show a large difference, when the color variance of the face candidate is small, when the occupancy ratio of the skin color region is large and when the change in the size of the face region is large after the elapse of a predetermined time, the non-face judging section 120 judges such face candidates as non-faces and removes them from the face candidates.

A pedestrian notification apparatus, which is configured to be used in a vehicle, includes an ambient object detector, a notification target detector and a notifier. The ambient object detector is configured to detect ambient objects present around the vehicle. The notification target detector is configured to detect a notification target pedestrian based on the detection results of the ambient object detector. The notifier is configured to notify the notification target pedestrian that the notification target pedestrian has been detected by the notification target detector.

A system and method for determining a classifier to discriminate between two classes—object or non-object. The classifier may be used by an object detection program to detect presence of a 3D object in a 2D image (e.g., a photograph or an X-ray image). The overall classifier is constructed of a sequence of classifiers (or “sub-classifiers”), where each such classifier is based on a ratio of two graphical probability models (e.g., Bayesian networks). A discrete-valued variable representation at each node in a Bayesian network by a two-stage process of tree-structured vector quantization is discussed. The overall classifier may be part of an object detector program that is trained to automatically detect many different types of 3D objects (e.g., human faces, airplanes, cars, etc.). Computationally efficient statistical methods to evaluate overall classifiers are disclosed. The Bayesian network-based classifier may also be used to determine if two observations (e.g., two images) belong to the same category. For example, in case of face recognition, the classifier may determine whether two photographs are of the same person. A method to provide lighting correction or adjustment to compensate for differences in various lighting conditions of input images is disclosed as well. As per the rules governing abstracts, the content of this abstract should not be used to construe the claims in this application.

A processing apparatus includes a distance image acquirer, a moving-object detector, and a danger-level determining unit. The distance image acquirer acquires a distance image containing distance information of each pixel. The moving-object detector detects a moving object from the distance image. The danger-level determining unit determines a danger level of the moving object by use of the distance image, and outputs the danger level to a controller that controls a controlled unit in accordance with the danger level.

Embodiments of this invention relate to detecting and blurring images. In an embodiment, a system detects objects in a photographic image. The system includes an object detector module configured to detect regions of the photographic image that include objects of a particular type at least based on the content of the photographic image. The system further includes a false positive detector module configured to determine whether each region detected by the object detector module includes an object of the particular type at least based on information about the context in which the photographic image was taken.

A stereoscopic camera includes first and second image pickup units, having respectively first and second optical axes, for photographing an object to form two image frames. Two angle adjusters make angle adjustment of the optical axes. An object detector detects a human face as a principal object in the two image frames. An arithmetic processor obtains a shift amount of the face between two image frames, and determines an axial correction angle according to the shift amount for the angle adjustment in consideration of the face. A checker checks whether the angle adjustment should be made for both optical axes or for one thereof. A controller operates at least one of the two angle adjusters according to the axial correction angle and in response to information from the checker, for positioning the face equally between the two image frames optically by adjusting the first and / or second optical axis.

A gesture recognition apparatus including a detector, a controller and a gesture recognizer, and is able to detect a portion to be detected using an image captured at a first resolution without reducing the number of images to be entered per unit of time to an object detector by detecting an auxiliary portion instead when the portion to be detected is not detected at a second resolution, estimating the position of the auxiliary portion based on the position of the auxiliary portion, and extracting the periphery thereof from the image captured at the first resolution.

An apparatus includes an object detector configured to receive image data of a scene viewed from the apparatus and including an object. The image data is associated with multiple scale space representations of the scene. The object detector is configured to detect the object responsive to location data and a first scale space representation of the multiple scale space representations.

An object position area (82a) is calculated according to a position in the space of a detected truck (70). A template (80a) corresponding to the object position area (82a) recorded at the previous time is then called. The template (80a) is moved to a position on a reference image Ib where the similarity is highest. Overlap rate (R(t-1)⊥Rt) of the object position area (82a) and the template (80a) is calculated. A decision is made whether the object is identical to that detected in the past by using the overlap rate.

A vehicle surroundings monitoring apparatus has: a point-of-view converter that converts an image shot with a camera installed on a vehicle into a bird's-eye-view image through point-of-view conversion; a position adjuster that performs position adjustment between two bird's-eye-view images produced from two images shot at different time points, the position adjuster performing the position adjustment based on the two bird's-eye-view images; and a three-dimensional object detector that detects a three-dimensional object around the vehicle based on differences between the two bird's-eye-view images having undergone the position adjustment.

Methods for image processing for detecting and recognizing an image object include detecting an image object using pose-specific object detectors, and performing fusion of the outputs from the pose-specific object detectors. The image object is recognized using pose-specific object recognizers that use outputs from the pose-specific object detectors and the fused output of the pose-specific object detectors; and by performing fusion of the outputs of the pose-specific object recognizers to recognize the image object.

An object detection apparatus mountable to a moveable apparatus for detecting an object existing outside the moveable apparatus by capturing a plurality of images using a plurality of imaging devices mounted to the moveable apparatus and generating a disparity image from the captured images includes a map generator to generate a map indicating a frequency profile of disparity values correlating a horizontal direction distance of the object with respect to a movement direction of the moveable apparatus, and a distance to the object in the movement direction of the moveable apparatus based on the disparity image, an isolated area detection unit to detect an isolated area based on the frequency profile, an isolated area divider to divide the isolated area into two or more isolated areas based on the frequency profile in the isolated area, and an object detector to detect an object based on the divided isolated area.

Techniques and systems are provided for tracking objects in a sequence of video frames. For example, an object tracker maintained for the sequence of video frames is identified. An object tracked by the object tracker is detected based on an application of an object detector to at least one key frame in the sequence of video frames. The object detector can include a complex object detector. A status of the object tracker can be updated to a still status in a current video frame of the sequence of video frames. A tracker having the still status is associated with an object that is static in one or more video frames of the sequence of video frames. The object can be tracked in the current video frame using the object tracker based on the status of the object tracker being updated to the still status in the current video frame. For example, a bounding region of the object tracker in the current frame can be replaced with a previous bounding region of the object tracker in a previous frame based on the status of the object tracker being updated to the still status in the current video frame.

A layout tool includes an object detector constructed and arranged to detect the location of a vertically extending edge portion of an object hidden from view behind a generally vertically extending wall surface, a light source that is capable of projecting a line of light along the wall surface, and an angular orientation mechanism operably coupled to the light projection mechanism. The angular orientation mechanism is operable to establish that the line of light is vertical. The light source and the object detector are operatively interengaged such that when a vertically extending edge is detected by the object detector, a vertically extending line of light projected on the surface by the light source indicates the location of a vertically extending edge portion of the hidden object.

A travel safety apparatus for a vehicle includes: a first object detector having a first detection area defined by a first detection angle; a second object detector having a second detection area defined by a second detection angle; a motion state determination unit; a collision determination unit determining whether there is possibility of collision of an object detected in at least one of the first detection area and the second detection area to the vehicle based on the motion state; a controller controlling the vehicle so that a collision is avoided; and an object identity determination unit determining whether the first object and the second object are identical, wherein when a first object detected in the first detection area and a second object detected in the second detection area are determined identical, the collision determination unit determines whether there is possibility of collision of the first object to the vehicle.

An on-vehicle device mounted on a vehicle includes an imaging unit that captures an image of a wide angle range through a curved light receiver, a moving-object detector that detects a moving object approaching an own vehicle from a mounting direction of the imaging unit and from any direction other than the mounting direction, based on the image captured by the imaging unit, a collision-risk determination unit that determines a degree of collision risk indicating a possibility of collision between the moving object detected by the moving-object detector and the own vehicle, and a moving-object warning unit that warns presence of the moving object included in an image portion in which a distortion of the image is a predetermined value or more, and warns the presence of the moving object according to the degree of collision risk determined by the collision-risk determination unit.

An apparatus includes an object detector configured to receive image data of a scene viewed from the apparatus and including an object. The image data is associated with multiple scale space representations of the scene. The object detector is configured to detect the object responsive to location data and a first scale space representation of the multiple scale space representations.

A system is provided for automatic selection of medical images. The system comprises an input (302) for receiving a temporal sequence of medical images acquired with a hand-held medical imaging device. An object detector (303) is provided for detecting an object in at least one of the images. An image selector (304) is provided for selecting an image in which the object has been detected by the object detector. A snapshot means (305) is provided for storing the selected image as a snapshot. Moreover, a hand-held medical imaging device is provided for generating the sequence of medical images.

A system and method for assisting the driver of a vehicle in identifying obstacles for the vehicle as is described. Objects located outside the vehicle are detected with the aid of object detector. If objects are detected, information is given to the driver and / or to defined components of the vehicle. An evaluation unit ascertains whether a detected object is a road bump, and information is given to the driver and / or to components of the vehicle only if a detected object is a road bump.

A system and method for determining a classifier to discriminate between two classes—object or non-object. The classifier may be used by an object detection program to detect presence of a 3D object in a 2D image (e.g., a photograph or an X-ray image). The overall classifier is constructed of a sequence of classifiers (or “sub-classifiers”), where each such classifier is based on a ratio of two graphical probability models (e.g., Bayesian networks). A discrete-valued variable representation at each node in a Bayesian network by a two-stage process of tree-structured vector quantization is discussed. The overall classifier may be part of an object detector program that is trained to automatically detect many different types of 3D objects (e.g., human faces, airplanes, ears, etc.). Computationally efficient statistical methods to evaluate overall classifiers are disclosed. The Bayesian network-based classifier may also be used to determine if two observations (e.g., two images) belong to the same category. For example, in case of face recognition, the classifier may determine whether two photographs are of the same person. A method to provide lighting correction or adjustment to compensate for differences in various lighting conditions of input images is disclosed as well. As per the rules governing abstracts, the content of this abstract should not be used to construe the claims in this application.

An object detector detects an object with a camera and calculates position data showing its direction and distance. A laser radar obtains an front image and recognizes an identified image in the front image. Coordinates of this identified image are calculated and converted to data indicating direction to the object. The identified image is correlated with the object detected by the laser radar and the correlated object is identified as an identified object. Position data of this correlated object are outputted as data on the identified object.

A method and system for training a special object detector to distinguish a foreground object appearing in a sequence of frames for a target domain. The sequence of frames depicts motion of the foreground object in a non-uniform background. The foreground object is detected in a high-confidence subwindow of an initial frame of the sequence, which includes computing a measure of confidence that the high-confidence subwindow includes the foreground object and determining that the measure of confidence exceeds a specified confidence threshold. The foreground object is tracked in respective positive subwindows of subsequent frames appearing after the initial frame. The subsequent frames are within a specified short period of time. The positive subwindows are used to train the special object detector to detect the foreground object in the target domain. The positive subwindows include the subwindow of the initial frame and the respective subwindows of the subsequent frames.

A system, controller, and method for controlling a light distribution pattern. A light source and an electrowetting lens cooperate to vary a light distribution pattern of light from the light source. An object detector is used by a controller determine the location of an object and operate the electrowetting lens in order to control the light distribution pattern based on the location of the object. The electrowetting lens provides for faster redirecting of light toward an object when compared to mechanical based system. The light source may be an array of light emitting diodes to provide a reliable, energy efficient source of light.

A travel safety apparatus for a vehicle includes: a first object detector having a first detection area defined by a first detection angle; a second object detector having a second detection area defined by a second detection angle; a motion state determination unit; a collision determination unit determining whether there is possibility of collision of an object detected in at least one of the first detection area and the second detection area to the vehicle based on the motion state; a controller controlling the vehicle so that a collision is avoided; and an object identity determination unit determining whether the first object and the second object are identical, wherein when a first object detected in the first detection area and a second object detected in the second detection area are determined identical, the collision determination unit determines whether there is possibility of collision of the first object to the vehicle.