87 results about "Stationary object" patented technology

The present application relates to an apparatus for determining the ego-motion of a radar apparatus, the apparatus configured to: process radar-point-cloud information comprising a plurality of points by neural network models, the processing comprising: pointwise mapping the features thereof to a greater number of mapped-features to provide mapped-radar-point-cloud information, determining a global feature vector indicative of characteristics of the mapped-radar-point-cloud information, generating a feature matrix wherein each point therein is characterized by a feature-set based on a combination of the features, the mapped-features and the global feature vector, determining a pointwise-weight representing a likelihood that the point represents a stationary object in the space, a pointwise-offset comprising a correction to be applied to the Doppler velocity measurement to at least reduce the Doppler velocity measurement for points having a greater than expected Doppler velocity, and providing an estimate of the motion of the radar apparatus.

The utility model discloses intelligent sensing radar monitoring equipment, and relates to the technical field of monitoring equipment, the radar monitoring equipment comprises a shell, and the interior of the shell is hollow; the monitoring camera is fixedly arranged on the shell and is used for monitoring a preset monitoring area; the circuit board is fixedly arranged in the shell, and a radar sensing device and a main control device are arranged on the circuit board; the radar sensing device is used for sensing a moving object or a static object in the predetermined monitoring area, and the main control device is connected with the monitoring camera and the radar sensing device through different interfaces and is used for sending the moving object or the static object to the radar sensing device under the condition that the radar sensing device senses an object of a preset type. And controlling the monitoring camera to start video recording. The utility model aims to improve the sensing accuracy of the sensing monitoring equipment.

A computer-implemented method is provided for estimating velocity of a moving object. The method includes receiving an image, which includes a first strip generated by a first sensor and a second strip generated by a second sensor, and recognizing a moving object in the first strip of the image. The method also includes selecting a plurality of stationary objects that are captured with the moving object in the first strip of the image, while excluding stationary object(s) in the second strip of the image, wherein the plurality of stationary objects are non-moving features. The method further includes combining misregistration values for the plurality of stationary objects in the first strip of the image and calculating a velocity of the moving object, based on a raw velocity of the moving object and the combined misregistration values.

The techniques and systems herein enable ghost object detection. Specifically, a reflection line is determined that indicates a potential reflection surface between a first mobile object and a second mobile object. If enough stationary objects are within a region of the reflection line, then it is determined whether one or more of the stationary objects within the region are within a distance of a reflection point. The expected velocity of the second object is then determined and checked against the velocity of the second object. If the expected velocity is close to the velocity, then the second object is determined to be a ghost object. By doing so, the system can effectively identify ghost objects in a variety of environments, allowing downstream operations to function as designed.

[PROBLEM] Provided are a light detection device for accurately focusing by using an event signal while imaging a stationary object, an electronic apparatus, and a control method of the light detection device. [SOLUTION] A light detection device according to one aspect disclosed herein comprises: a light reception unit that photoelectrically converts incident light to generate an electric signal; a conversion circuit that converts the electric signal into a voltage signal; a first buffer circuit that outputs a first detection signal corresponding to the voltage signal; a second buffer circuit that outputs a second detection signal corresponding to an arbitrary first pseudo signal that does not depend on the voltage signal; and a subtractor that outputs a first output signal when the first or second detection signal exceeds a first threshold voltage higher than the first or second detection signal, and outputs a second output signal when the first or second detection signal is below a second threshold voltage lower than the first or second detection signal.

The vehicle-mounted object recognition device is mounted on a vehicle having an imaging unit. A calculation device of a vehicle-mounted object recognition device detects a stationary object on the basis of an image captured by an imaging unit, estimates a torque arm length, which is the distance from the center of rotation of a vehicle to the imaging unit, and determines the ground speed of the object on the basis of the estimated torque arm length.

An apparatus to be viewed by a driver to aid parking a car parallel to the walls of a garage, as well as the correct distance into the garage. The driver is able to park in exactly the same spot each time, at the desired distance from other cars, walls, or other stationary objects via the aid apparatus. This helps minimize banging car doors on objects upon opening, or bumping into anything in front of the vehicle, while maximizing use of space within the garage. The apparatus is installed in a fixed position in front of the driver at eye level as they sit comfortably in a driver's seat of the vehicle. As the driver drives their car into their garage to park, they are guided by visual cues from the apparatus to park the car in the same footprint on the floor each time.

The invention relates to a method for detecting false detection situations of a vehicle ultrasonic sensor (9). In this method, first sensor signals recorded at the beginning of a parking period are compared with second sensor signals recorded at the end of the parking period from the ultrasonic sensor (9) for static objects (2, 7) in the immediate vicinity. If this comparison reveals a deviation of the second sensor signals from the first sensor signals, it is concluded that the ultrasonic sensor (9) is covered with snow, and a predetermined safety measure is executed. The invention also relates to an assistance system (11) for carrying out the method and a correspondingly equipped motor vehicle (4).

The invention relates to a computer-implemented method for determining and learning vehicle parameters of an ego vehicle (V) in the ego vehicle (V), comprising the following steps: - Recording (S1) a series of environmental representations of the environment of the ego vehicle (V) using at least one environmental sensor (2) during a defined period at different time steps; - Measuring (S2) the wheel rotation angle with at least one wheel speed sensor (3) during the defined period at different time steps; - Identifying (S3) features (6) of stationary objects (5a-5d) by analyzing the series of environment representations; - continuous localization (S4) of the ego vehicle (V) based on the detected features (6) of the stationary objects (5a-5d) at the different time steps; - Generating (S5) a first trajectory (T1) driven by the ego vehicle (V) based on the continuous localization of the ego vehicle (V); - Generating (S6) a second trajectory (T2) by calculating the distance traveled using the measured wheel rotation angles and known vehicle parameters; - Comparing (S7) the first (T1) and the second trajectory (T2) and determining deviations between the two trajectories (T1, T2); - Setting (S8) at least one of the trajectories (T1, T2) to adapt it to the other trajectory, and generating a set trajectory (TA); - Calculating (S9) vehicle parameters; - Learning (S10) the calculated vehicle parameters by updating the known vehicle parameters.

The driving assistance device 1 controls the notification device 30 to issue a predetermined alert to the occupants of the own vehicle if, at a first point in time, it detects the existence of a first driving lane L1 adjacent to the lane L0 in which the own vehicle is traveling, and no stationary object is present in a predetermined area R[n+10] located ahead of the own vehicle in that first driving lane L1, and then, at a second point in time after the first point in time, when the own vehicle is positioned on the side of this predetermined area, it detects the presence of a solid object OB within said area and that the distance Δd between this solid object OB and the own vehicle is less than a threshold.

A method for monitoring user performance in launching objects at sporting events includes capturing, with an image sensor on glasses worn by a user at a sporting event, two-dimensional (2-D) images of an object launched by a player participating in the sporting event. The launched object and a stationary object at the sporting event are identified. An orientation of the image sensor is determined based on a shape of the stationary object within the 2D images, and locations of the launched object in 3D space are determined based on the 2D images and the determined orientation of the image sensor. The trajectory of the launched object in 3D space is then determined, and the trajectory is used to determine a parameter indicative of a performance of the player for the sporting event. Feedback indicative of the performance of the player is then provided based on the determined parameter.

Methods and systems are disclosed for employing an ultrasonic sensor to estimate a range for a moving object. At least one processor separates returned signals received by an ultrasonic transducer into a stationary object signal and a moving object signal. A gain is determined based at least in part on the stationary object signal. The stationary object signal is combined with the moving object signal using the gain and then filtered. The range for the moving object is estimated using the filtered combined stationary and moving object signal.

The present invention executes: first angular error estimation processing (S40) for determining an estimated first angular error value obtained by estimating an angular error in a radar device using azimuthal dependence of relative velocity with respect to a stationary object; second angular error estimation processing (S50) for calculating a stationary object movement direction in which the stationary object moves when viewed from a moving body if the moving body is assumed to be travelling straight, calculating the next distance to the stationary object at the next azimuth on the basis of the movement direction average value and the distance to the stationary object, calculating a true estimated angle value on the basis of the next distance and a reference movement direction in which the stationary object moves when there is no angular error, and determining an estimated second angular error value on the basis of the difference between the true estimated angle value and the next azimuth; and angular error integration processing (S60) for using the estimated first angular error value and / or the estimated second angular error value to estimate an angular error in an object detected by the radar device.

To reduce an operation amount required for estimating a three dimensional field.SOLUTION: The image processing apparatus 102 according to the present disclosure acquires a plurality of captured images obtained by imaging from a plurality of directions, sets, for each object, a three dimensional space including the object as a learning space on the basis of the plurality of captured images, and learns, for each set learning space, a three dimensional field corresponding to the learning space on the basis of the plurality of captured images. Here, when the image processing apparatus 102 learns a three dimensional field corresponding to a learning space based on a plurality of captured images obtained by synchronized imaging at a certain time point, for a learning space in which an object included in the learning space is a stationary object, the image processing apparatus 200 learns a feature amount of a three dimensional field corresponding to a learning space including a moving object using a feature amount of a three dimensional field already obtained as a result of learning based on a plurality of captured images obtained by synchronized imaging at another time point as a feature amount of a three dimensional field corresponding to the learning space.SELECTED DRAWING: Figure 4

The invention relates to the technical field of automotive electronics, and particularly discloses an angle self-calibration method and system for a vehicle-mounted millimeter-wave radar, and the method comprises the steps: collecting the measurement data of a static object in a view field range through the radar when a vehicle carrying the vehicle-mounted millimeter-wave radar runs in a straight line, the measurement data includes a measured azimuth angle and a relative velocity of each stationary object. According to the method, the key function is constructed by collecting the measurement data of the static object, the angle error coefficient and the vehicle speed error coefficient are jointly estimated in combination with the nonlinear least square method, the parameter estimation precision is improved through data optimization means such as azimuth interval classification and filtering smoothing, and finally accurate compensation of the radar measurement azimuth is achieved. The problem of error drift in the dynamic driving process of the millimeter wave radar can be effectively solved, the identification precision of the radar on static vehicles and roadside obstacles is improved, and the functional reliability of vehicle-mounted safety systems such as ACC and vehicle distance early warning is guaranteed.

The invention provides a target object tracking method and electronic equipment, and the method is applied to the technical field of computer vision, and comprises the steps: carrying out the target detection and non-maximum suppression processing of a current frame image, so as to obtain a plurality of detection frames; based on the target loss function, matching the plurality of detection frames with the plurality of trackers; the target loss function comprises a first loss component and a second loss component, and the first loss component is calculated based on an intersection-to-union ratio between each detection frame and each tracker prediction frame; the second loss component is calculated based on an angle difference between a first velocity vector calculated by historical position parameters of each detection frame and a second velocity vector predicted by a tracker; and for the tracker which is not successfully matched, maintaining the current state of the tracker and updating the unmatched duration of the tracker. According to the method, a plurality of detection frames can be matched with a plurality of trackers based on the target loss function, so that the detection frame of a static object is prevented from being taken away by the detection frame of a moving object.

The present disclosure relates to stationary object detection, in particular to a method of detecting stationary objects implemented by a control system of an autonomous vehicle, comprising: receiving sensor signal data including stationary detections and non-stationary detections from a surrounding environment of the vehicle; determining at least one stationary detection combination that satisfies one or more lateral position selection criteria based on a lateral position of each stationary detection from a direction that the vehicle faces; determining at least one stationary detection combination that satisfies one or more combination regularity selection criteria based on a regularity of a position difference between pairs of stationary detections in the combination that are sequentially positioned in the direction that the vehicle faces; determining one or more stationary detection combinations that satisfy the lateral selection criteria and the combination regularity selection criteria for combinations of stationary detections corresponding to at least one stationary object; removing stationary detections corresponding to the at least one stationary object from the sensor signal data output to one or more data processing components of the control system.

The application provides a mobile object detection method, which comprises the following steps: acquiring point cloud data set and a first image of a target scene; identifying a stationary object region in the first image; recording point cloud data corresponding to the stationary object region in the point cloud data set as first point cloud data; obtaining a first speed range according to the first point cloud data; and judging whether a mobile object exists in the target scene according to second point cloud data and the first speed range, wherein the second point cloud data is point cloud data in the point cloud data set except the first point cloud data. The application also discloses a mobile object detection device, a computer storage medium and an electronic device. The point cloud data obtained by combining a radar can improve the accuracy of detecting a mobile object.

A method for monitoring user performance in launching objects at sporting events includes capturing, with an image sensor on glasses worn by a user at a sporting event, two-dimensional (2-D) images of an object launched by a player participating in the sporting event. The launched object and a stationary object at the sporting event are identified. A location of the image sensor is determined based on the stationary object within at least one of the 2D images, and locations of the launched object are determined based on the 2D images and the determined location of the image sensor. An outcome of the launched object is then determined, and the outcome is used to determine a parameter indicative of a performance of the player for the sporting event. Feedback indicative of the performance of the player is then provided based on the determined parameter.

An apparatus to be viewed by a driver to aid parking a car parallel to the walls of a garage, as well as the correct distance into the garage. The driver is able to park in exactly the same spot each time, at the desired distance from other cars, walls, or other stationary objects via the aid apparatus. This helps minimize banging car doors on objects upon opening, or bumping into anything in front of the vehicle, while maximizing use of space within the garage. The apparatus is installed in a fixed position in front of the driver at eye level as they sit comfortably in a driver's seat of the vehicle. As the driver drives their car into their garage to park, they are guided by visual cues from the apparatus to park the car in the same footprint on the floor each time.

The present application relates to the technical field of object detection. Disclosed are a method and apparatus for detecting a stationary object, and a device, a storage medium and a vehicle. The method comprises: acquiring the current image frame collected by a camera, and identifying a camera observation object from the current image frame; associating the camera observation object with a current object detection box, and performing state prediction and update on the associated object detection box on the basis of a relative motion parameter of the camera observation object, wherein the current object detection box comprises a detection box created on the basis of historical observed objects; determining whether the state of the updated object detection box has converged; and when the state of the updated object detection box has converged, determining whether the updated object detection box is stationary. In the present application, an observation object is associated with an object detection box and a state is updated, such that whether the object detection box is stationary can be accurately determined by using the object detection box with a converged state.

The invention relates to the field of airport road foreign matter detection, and provides a machine learning-based FOD detection algorithm, which comprises an input module used for receiving basic image data of an airport runway; the processing module is used for carrying out preprocessing and feature extraction on the input data; the storage module is used for storing the original image data and the detection result; the acquisition module is used for acquiring image and sound data of an airport runway in real time; and the recognition module is used for recognizing moving objects and static objects in the collected data based on a machine learning model. And high-precision real-time detection is realized through cooperation of multiple modules. The acquisition module adopts a high-definition camera to ensure that image data is clear; the processing module utilizes a convolutional neural network (CNN) to extract features, and can accurately recognize moving and static objects in combination with a YOLOv5 algorithm of the recognition module. The comparison module compares the real-time image with the original image, abnormity is judged if the real-time image is lower than the threshold value, the runway foreign matter can be found in time, and the system can rapidly position the FOD in the complex environment.

An in-vehicle object detection device is provided, mounted on a vehicle equipped with an imaging unit. An arithmetic operating device of the in-vehicle object detection device detects a stationary object based on an image acquired by the imaging unit, estimates a moment arm length (the distance from the vehicle's turning center to the imaging unit), and obtains a ground velocity of the object based on the estimated moment arm length.

An image noise learning server includes an image input interface configured to receive training images, and at least one processor configured to control an image extractor to extract, from the training images, a first image including a stationary object and a second image including a moving object, a noise filter to obtain a third image by applying noise filtering with a first intensity to the second image, the third image including the moving object, a labeling unit to determine an intensity of a side effect based on a difference between the stationary object included in the first image and the moving object included in the third image, and a machine learning unit to receive, as a label, the determined intensity of the side effect and image attributes of the training images, and obtain artificial intelligence (AI) parameters by performing machine learning on the second image based on the received label.

In some embodiments, a sensing device, and in particular, a modular spectral imaging device is described. The sensing device compiles one or more spectral images of an object in a point-by-point scan. The sensing device and related methods for scanning stationary objects provides spectral and spatial discrimination. Unlike conventional line scan or snapshot style devices, this system includes a sensor configured to function as a single pixel photodetector to sample a single point of a sample object. Spectral discrimination refers to isolating specific wavelengths of light within a spectral sensitivity range of a detector. Spatial discrimination refers to imaging an object within multidimensional space. The sensing device allows for configurability of both spectral bands and spatial resolution across a wide range of spectral sensitivities. Temporal scanning techniques are used to build up a multi-dimensional image. Modularity and automation are used to provide a broad range of capabilities.

This document describes the techniques and systems associated with a radar system using a machine learning model for stationary object detection. The radar system includes a processor capable of receiving radar data in the form of time-series frames associated with electromagnetic (EM) energy. The processor uses the radar data to generate a range-time map of the EM energy, which is then input to the machine learning model. The machine learning model is capable of receiving features corresponding to stationary objects extracted from the range-time map of multiple range intervals at each time-series frame as input. In this manner, the described radar system and techniques are able to accurately detect stationary objects of various sizes and extract key features corresponding to the stationary objects.

The present invention provides an object detection method and an object detection device capable of distinguishing between moving objects and stationary objects. [Solution] The probability of an object being present in a defined section is calculated by dividing the area in front of the vehicle V1 in the direction of travel into a grid pattern, based on the positional information of the distance measurement points of objects present around the vehicle V1. Optical flow F of objects present around the vehicle V1 is obtained from the image captured by the vehicle V1's imaging device 12. A set of sections is generated by associating multiple sections based on the probability of occupancy and at least one of the speed and amount of movement of the object in the vehicle width direction in the image, calculated from the optical flow F.

Example embodiments of the present disclosure relate to apparatuses, methods, and computer-readable storage media for adjusting a sensing coverage area. In this technical solution, an apparatus including a sensing management function can determine that a sensing coverage area of a sensing system is to be adjusted to sense a moving target, and the apparatus can send a sensing static power adjustment indication to a sensing transition device, where the sensing static power adjustment indication indicates to the sensing transition device to adjust a static power of signals reflected from one or more stationary objects in the sensing coverage area. The sensing transition device can adjust the static power of the signals reflected from the one or more stationary objects in the sensing coverage area based on the sensing static power adjustment indication. Thus, the sensing coverage area can be adjusted as a static power adjustment.

A method with grid map generation includes: determining position information of a moving object corresponding to a first time step based on a position sensor of the moving object; determining detection information of nearby objects present around the moving object corresponding to the first time step based on a radio detection and ranging (radar) sensor of the moving object; selecting a still object in a moving range of the moving object from among the nearby objects, based on the position information and the detection information; updating a point cloud determined based on the radar sensor in a previous time step of the first time step, based on the position information and on detection information of the still object comprised in the detection information of the nearby objects; and generating a grid map based on an occupancy probability for each grid of the updated point cloud.