13335results about "Scene recognition" patented technology

A vehicle lane change aid system includes a detector that is operative to detect the presence of an other vehicle adjacent the vehicle, an indicator for providing an indication that a lane change maneuver of the vehicle may affect the other vehicle and a control receiving movement information of the vehicle. The control develops a position history of the vehicle at least as a function of the movement information. The control compares the detected presence of the other vehicle with the position history and provides an indication when a lane change maneuver may affect the other vehicle.

A navigation system for a vehicle includes a vehicle-based telematics system, a vehicle-based global positioning system and a control. The telematics system is operable to receive a user input from a driver of the vehicle and to download directional information from an external service provider to the control in response to the user input and an initial geographic position of the vehicle. The directional information comprises at least two instructions with each of the instructions being coded or associated with or linked to a respective geographic location. The control is operable to provide an output corresponding to each of the instructions in response to a current actual geographic position of the vehicle. The control is operable to provide each instruction only when the then current actual geographic position of the vehicle at least generally corresponds to the particular geographic location associated with the instruction.

A vision system for a vehicle includes an imaging device having an imaging sensor, a camera microcontroller, a display device having a display element, a display microcontroller, and at least one user input selectively actuatable by a user. The imaging device communicates an image signal to the display device via a communication link. The display microcontroller affects the image signal in response to the at least one user input. The camera microcontroller monitors the image signal on the communication link and adjusts a function of the imaging device in response to a detection of the affected image signal. The vision system may adjust a display or sensor of the system in conjunction with a distance detecting system.

An alert system for a vehicle includes a video display, an interior visual alert device disposed at an interior rearview mirror assembly, a driver side visual alert device disposed at a driver side exterior rearview mirror assembly and a passenger side visual alert device disposed at a passenger side exterior rearview mirror assembly. A control is operable to activate at least one of the alert devices in response to a detection of an object rearward of the vehicle. The alert devices are viewable by the driver of the vehicle when activated and are operable to guide or prompt the driver to check the images captured by a rearward facing camera and displayed in the vehicle cabin by the video display so that the driver can verify the nature and type of a potential hazard rearward of the vehicle.

A vision system for a vehicle includes an imaging device having an imaging sensor, a camera microcontroller, a display device having a display element, a display microcontroller, and at least one user input selectively actuatable by a user. The imaging device communicates an image signal to the display device via a communication link. The display microcontroller affects the image signal in response to the at least one user input. The camera microcontroller monitors the image signal on the communication link and adjusts a function of the imaging device in response to a detection of the affected image signal. The vision system may adjust a display or sensor of the system in conjunction with a distance detecting system.

Driver distraction is reduced by providing information only when necessary to assist the driver, and in a visually pleasing manner. Obstacles such as other vehicles, pedestrians, and road defects are detected based on analysis of image data from a forward-facing camera system. An internal camera images the driver to determine a line of sight. Navigational information, such as a line with an arrow, is displayed on a windshield so that it appears to overlay and follow the road along the line of sight. Brightness of the information may be adjusted to correct for lighting conditions, so that the overlay will appear brighter during daylight hours and dimmer during the night. A full augmented reality is modeled and navigational hints are provided accordingly, so that the navigational information indicates how to avoid obstacles by directing the driver around them. Obstacles also may be visually highlighted.

In a computerized system including a camera mounted in a moving vehicle. The camera acquires consecutively in real time image frames including images of an object within the field of view of the camera. Range to the object from the moving vehicle is determined in real time. A dimension, e.g. a width, is measured in the respective images of two or more image frames, thereby producing measurements of the dimension. The measurements are processed to produce a smoothed measurement of the dimension. The dimension is measured subsequently in one or more subsequent frames. The range from the vehicle to the object is calculated in real time based on the smoothed measurement and the subsequent measurements. The processing preferably includes calculating recursively the smoothed dimension using a Kalman filter.

Methods and systems are described for generating a vehicle-to-vehicle traffic alert. Various aspects may include detecting that an abnormal traffic condition exists in an operating environment of a vehicle and generating a related electronic message. The electronic message may be transmitted via the vehicle's transceiver using a wireless communication to a nearby vehicle to alert the nearby vehicle of the abnormal traffic condition and to allow the nearby vehicle to avoid the abnormal traffic condition.

The technology of the 4D-GIS system deploys a GIS-based algorithm used to determine the location of a moving target through registering the terrain image obtained from a Moving Target Indication (MTI) sensor or small Unmanned Aerial Vehicle (UAV) camera with the digital map from GIS. For motion prediction the target state is estimated using an Extended Kalman Filter (EKF). In order to enhance the prediction of the moving target's trajectory a fuzzy logic reasoning algorithm is used to estimate the destination of a moving target through synthesizing data from GIS, target statistics, tactics and other past experience derived information, such as, likely moving direction of targets in correlation with the nature of the terrain and surmised mission.

A method of estimating a time to collision (TTC) of a vehicle with an object comprising: acquiring a plurality of images of the object; and determining a TTC from the images that is responsive to a relative velocity and relative acceleration between the vehicle and the object.

A vehicle monitoring apparatus for obtaining a distance image including an image data and three-dimensional distance information and for monitoring surrounding conditions on the basis of the distance image, comprises: means for dividing the distance image into a plurality of blocks composed of picture elements, means for collecting the blocks having a similar distance data and for grouping the blocks into an independent group, means for calculating an area size of the independent group, means for extracting the image data as an object data if the area size of the group is larger than a predetermined value and for discarding the image data as a false data if the area size is smaller than the predetermined value, means for preparing a histogram having a lateral axis representing a deviation amount and a longitudinal axis representing a frequency corresponding to a number of the image data, and means for detecting an object and a distance to the object by deleting the frequency having a smaller number of the image data than a threshold value along the lateral axis on the histogram. Thereby, false data can be removed from the image data and a mismatching can be prevented.

A method in computerized system mounted on a vehicle including a cabin and an engine. The system including a visible (VIS) camera sensitive to visible light, the VIS camera mounted inside the cabin, wherein the VIS camera acquires consecutively in real time multiple image frames including VIS images of an object within a field of view of the VIS camera and in the environment of the vehicle. The system also including a FIR camera mounted on the vehicle in front of the engine, wherein the FIR camera acquires consecutively in real time multiple FIR image frames including FIR images of the object within a field of view of the FIR camera and in the environment of the vehicle. The FIR images and VIS images are processed simultaneously, thereby producing a detected object when the object is present in the environment.

An apparatus, method for detecting critical areas and a pedestrian detection apparatus using the same are provided. An application of the pedestrian detection system is provided to help limit critical urban environment to particular areas. Contrary to traditional pedestrian detection systems that localize every pedestrians appearing in front of the subject vehicle, the apparatus first finds critical areas from urban environment and performs a focused search of pedestrians. The environment is reconstructed using a standard laser scanner but the subsequent checking for the presence of pedestrians is performed by incorporating a vision system. The apparatus identifies pedestrians within substantially limited image areas and results in boosts of timing performance, since no evaluation of critical degrees is necessary until an actual pedestrian is informed to the driver or onboard computer.

In a computerized system including a camera mounted in a moving vehicle. The camera acquires consecutively in real time image frames including images of an object within the field of view of the camera. Range to the object from the moving vehicle is determined in real time. A dimension, e.g. a width, is measured in the respective images of two or more image frames, thereby producing measurements of the dimension. The measurements are processed to produce a smoothed measurement of the dimension. The dimension is measured subsequently in one or more subsequent frames. The range from the vehicle to the object is calculated in real time based on the smoothed measurement and the subsequent measurements. The processing preferably includes calculating recursively the smoothed dimension using a Kalman filter.

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 method is provided using a system mounted in a vehicle. The system includes a rear-viewing camera and a processor attached to the rear-viewing camera. When the driver shifts the vehicle into reverse gear, and while the vehicle is still stationary, image frames from the immediate vicinity behind the vehicle are captured. The immediate vicinity behind the vehicle is in a field of view of the rear-viewing camera. The image frames are processed and thereby the object is detected which if present in the immediate vicinity behind the vehicle would obstruct the motion of the vehicle. The processing is preferably performed in parallel for a plurality of classes of obstructing objects using a single image frame of the image frames.

A method and system for sensing an obstacle comprises transmitting an electromagnetic signal from a mobile machine to an object. A reflected electromagnetic signal is received from the object to determine a distance between the object and the mobile machine. An image patch is extracted from a region associated with the object. Each image patch comprises coordinates (e.g., three dimensional coordinates) associated with corresponding image data (e.g., pixels). If an object is present, image data may include at least one of object density data and object color data. Object density data is determined based on a statistical measure of variation associated with the image patch. Object color data based on the color of the object detected with brightness normalization. An object is classified or identified based on the determined object density and determined object color data.

Systems and methods for cuboid detection and keypoint localization in images are disclosed. In one aspect, a deep cuboid detector can be used for simultaneous cuboid detection and keypoint localization in monocular images. The deep cuboid detector can include a plurality of convolutional layers and non-convolutional layers of a trained convolution neural network for determining a convolutional feature map from an input image. A region proposal network of the deep cuboid detector can determine a bounding box surrounding a cuboid in the image using the convolutional feature map. The pooling layer and regressor layers of the deep cuboid detector can implement iterative feature pooling for determining a refined bounding box and a parameterized representation of the cuboid.

In accordance with various embodiments of the disclosed subject matter, a method and a system for vision-centric deep-learning-based road situation analysis are provided. The method can include: receiving real-time traffic environment visual input from a camera; determining, using a ROLO engine, at least one initial region of interest from the real-time traffic environment visual input by using a CNN training method; verifying the at least one initial region of interest to determine if a detected object in the at least one initial region of interest is a candidate object to be tracked; using LSTMs to track the detected object based on the real-time traffic environment visual input, and predicting a future status of the detected object by using the CNN training method; and determining if a warning signal is to be presented to a driver of a vehicle based on the predicted future status of the detected object.

A portable multispectral data acquisition system for use on a vehicle such as an aircraft comprises a plurality of gyroscope-stabilized remote sensing devices synchronized to simultaneously capture images of a common spatial area in both visible and invisible bands of the electromagnetic spectrum, a computer and digital recorder to record and correlate the captured images with temporospatial reference information, image processing software to stack or layer the images and to extract and compare the images in order to identify and filter hidden or subsurface anomalies that are invisible to the naked eye, and additional image processing software to orthorectify the images to a three-dimensional digital terrain map and to stitch adjacent images together into a mosaic. Methods for using the portable multispectral data acquisition system are also provided.

Automatic conflation systems and techniques which provide vector-imagery conflation and map-imagery conflation. Vector-imagery conflation is an efficient approach that exploits knowledge from multiple data sources to identify a set of accurate control points. Vector-imagery conflation provides automatic and accurate alignment of various vector datasets and imagery, and is appropriate for GIS applications, for example, requiring alignment of vector data and imagery over large geographical regions. Map-imagery conflation utilizes common vector datasets as “glue” to automatically integrate street maps with imagery. This approach provides automatic, accurate, and intelligent images that combine the visual appeal and accuracy of imagery with the detailed attribution information often contained in such diverse maps. Both conflation approaches are applicable for GIS applications requiring, for example, alignment of vector data, raster maps, and imagery. If desired, the conflated data generated by such systems may be retrieved on-demand.

The present invention is a monocular computer vision technique. The technique is used to aid road vehicle driving for safety. An camera (e.g., camera or TV camera or camcorder) is installed in a vehicle facing to the road in front of the vehicle to capture a sequence of road / scene images for analyzing the driving situation. The situation includes the distance to a front obstacle or vehicle, the speed of the vehicle, and the left / right location of the vehicle in a road lane.

Provided is a technology for helping safe driving and realizing automatic driving of vehicles, or for counting the number of passing vehicles on the road or monitoring those passing vehicles for their driving. Using a plurality of cameras mounted in a vehicle or provided above a road, even if the relationship between the road plane and the respective cameras constantly changes in relative position or posture due to camera vibration or a change in road tilt, any obstacles located on the road such as other vehicles ahead, parked vehicles, and pedestrians on the road are detected without confusing those with textures including white lines, road signs, paint, road stains, and shadows of roadside objects, all of which do not disturb vehicle driving. An obstacle detection device 10 is structured by an image input section 11 for receiving images from a plurality of image pick-up devices 101, a correspondence detection section 12 for finding a plurality of pairs of corresponding points from the received right and left images, the slope degree calculation section 13 for calculating a slope degree of a plane including the corresponding points, and a result determination section 14 for determining as there being an obstacle when the calculated slope degree is larger than a predetermined value.

A method and system for measurement of ground based vehicle speed includes a movable platform that includes an unmanned aerial vehicle (UAV) located in proximity to a roadway, the UAV operates under control and navigation of a UAV control unit, and the UAV also carries camera and monitoring equipment, the camera and monitoring equipment including an onboard computing system, and a camera with a wide angle lens and a camera with a telephoto lens, the cameras being mounted on a pan / tilt device. An algorithm operated by the on-board computing system is used to detect and track vehicles moving on a roadway. The algorithm is configured to detect and track the vehicles despite motion created by movement of the UAV. The cameras mounted on the pan / tilt device are moved under the direction of the computer vision algorithm to maintain a target vehicle of the detected moving vehicles in view, and the speed of the target vehicle is measured.

One embodiment provides a method of capturing the presence of a drone, including: collecting, using at least one sensor, data associated with an aerial object; analyzing, using a processor, the data to determine at least one characteristic of the aerial object; accessing, in a database, a library of stored characteristics of commercially available drones; determining, based on the analyzing, if the at least one characteristic of the aerial object matches a characteristic of a commercially available drone; and responsive to the determining, generating an indication of a positive match. Other aspects are described and claimed.

A method is provided for preventing a collision between a motor vehicle and a pedestrian. The method uses a camera and a processor mountable in the motor vehicle. A candidate image is detected. Based on a change of scale of the candidate image, it may be determined that the motor vehicle and the pedestrian are expected to collide, thereby producing a potential collision warning. Further information from the image frames may be used to validate the potential collision warning. The validation may include an analysis of the optical flow of the candidate image, that lane markings prediction of a straight road, a calculation of the lateral motion of the pedestrian, if the pedestrian is crossing a lane mark or curb and / or if the vehicle is changing lanes.

A computer implemented method for detecting the presence of one or more pedestrians in the vicinity of the vehicle is disclosed. Imagery of a scene is received from at least one image capturing device. A depth map is derived from the imagery. A plurality of pedestrian candidate regions of interest (ROIs) is detected from the depth map by matching each of the plurality of ROIs with a 3D human shape model. At least a portion of the candidate ROIs is classified by employing a cascade of classifiers tuned for a plurality of depth bands and trained on a filtered representation of data within the portion of candidate ROIs to determine whether at least one pedestrian is proximal to the vehicle.

The present invention is a monocular computer vision technique. The technique is used to aid road vehicle driving for safety. An camera (e.g., camera or TV camera or camcorder) is installed in a vehicle facing to the road in front of the vehicle to capture a sequence of road / scene images for analyzing the driving situation. The situation includes the distance to a front obstacle or vehicle, the speed of the vehicle, and the left / right location of the vehicle in a road lane.