A method for automatically parking a vehicle in a parking slot involves manually driving the vehicle into the parking slot in a training step, and thereafter automatically driving the vehicle into the parking slot in a replay step. Automatically driving the vehicle into the parking slot involves detecting information of features of the environment of the vehicle corresponding to the driven trajectory, matching feature descriptors of the detected features of the environment with feature descriptors stored in the digital map, and re-localizing the vehicle against the trajectory stored in the digital map in order to navigate the vehicle along the stored trajectory into the parking slot. Automatically driving the vehicle into the parking slot is repeated multiple times, and involves deleting a feature descriptor stored in the digital map if the number of matches does not exceed a threshold after a predefined number of repetitions.

Provided is a method and system that includes an imaging device to be disposed in a lighting fixture to capture images, a remote computing device in communication with the imaging device, and comprising at least one processor. The processor is capable of processing data related to images from the at least one imaging device and from a satellite imagery system, performing comparison operation by detecting a first set of points of interest in an image from the at least one imaging device and corresponding second set of points of interest in an image of a same area from the satellite imagery system, and calculating a homography matrix by matching the first set of points of interests in the image from the at least one imaging device and the second set of points of interest in the image from the satellite imagery system, to determine latitude and longitude coordinates of the image from the imaging device.

An image processing device includes a sideline detector configured to detect sidelines of boundary lines of parking sections next to each other in a vehicle width direction by an edge detection process to an image, each of the sidelines being a pair of a rising edge and a falling edge, and to acquire an end point of each of the sidelines at which the pair is not detected, a rear-end edge identifying part configured to identify a rear-end edge of the parking section based on an end point away from the vehicle among the end points acquired by the sideline detector, and a parking frame setting portion configured to identify the parking section based on the two sidelines detected by the sideline detector and the rear-end edge identified by the rear-end edge identifying part, and to set a parking frame based on the parking section.

A method of detecting a frame line of a parking space from a captured image acquired by a camera includes detecting the frame line when the value of a parameter used for detection of the frame line falls within a first threshold range, estimating the position of an undetected frame line on the basis of the position of the detected frame line, and setting a threshold range used for detecting the frame line at the estimated position of the frame line to a second threshold range wider than the first threshold range.

A method for learning an automatic parking device of a vehicle for detecting an available parking area is provided. The method includes steps of: a learning device, (a) if a parking lot image of an area nearby the vehicle is acquired, (i) inputting the parking lot image into a segmentation network to output a convolution feature map via an encoder, output a deconvolution feature map by deconvoluting the convolution feature map via a decoder, and output segmentation information by masking the deconvolution feature map via a masking layer; (b) inputting the deconvolution feature map into a regressor to generate relative coordinates of vertices of a specific available parking region, and generate regression location information by regressing the relative coordinates; and (c) instructing a loss layer to calculate 1-st losses by referring to the regression location information and an ROI GT, and learning the regressor via backpropagation using the 1-st losses.

An information processing device includes: a memory; and a processor coupled to the memory and configured to: calculate a measurement value indicating a position of a first point of an object at a plurality of time points including a first time point and a second time point before the first time point on the basis of a monocular camera mounted on a moving body; calculate a predicted value of the position of the first point on the basis of the measurement value at the second time point and a movement amount of the moving body from the second time point to the first time point; and determine an adopted value at the position of the first point on the basis of a relationship between a difference between the measurement value and the predicted value at the first time point and a threshold.

An image processing device includes: a first generation unit which generates first target parking frame information based on an image taken by a first shooting unit that is provided at a side position of a vehicle; a second generation unit which generates second target parking frame information based on an image taken by a second shooting unit that is provided at a front or rear position of the vehicle; and a determination unit which determines a stop position in a parking frame by generating third target parking frame information to serve as a stop target based on the first target parking frame information generated by the first generation unit and the second target parking frame information generated by the second generation unit.

A method for provision image recordings in a vehicle. The method include: ascertaining a first image recording of a first image sensor of the vehicle and at least one further image recording of at least one further image sensor of the vehicle; carrying out a merging of the first image recording and the at least one further image recording for a reduction of an amount of data for providing the relevant information, the merging taking place based on a selection from the surrounding regions, whereby at least one merged image recording is obtained; initiating at least one transmission of the merged image recording within the vehicle and at least to a central control device of the vehicle, whereby the merged image recording is supplied to a processing for performing the vehicle function.

The present disclosure provides various approaches for smart area monitoring suitable for parking garages or other areas. These approaches may include ROI-based occupancy detection to determine whether particular parking spots are occupied by leveraging image data from image sensors, such as cameras. These approaches may also include multi-sensor object tracking using multiple sensors that are distributed across an area that leverage both image data and spatial information regarding the area, to provide precise object tracking across the sensors. Further approaches relate to various architectures and configurations for smart area monitoring systems, as well as visualization and processing techniques. For example, as opposed to presenting video of an area captured by cameras, 3D renderings may be generated and played from metadata extracted from sensors around the area.

Provided is an on-vehicle processing device that can estimate the position of a vehicle with higher accuracy. A storage unit stores a parking lot point group including a plurality of coordinates of points of a part of an object in a parking lot coordinate system. A sensor input unit acquires peripheral information from a camera. A movement information acquisition unit acquires movement information. A local peripheral information creation unit generates local peripheral information expressing second point group data including a position of the vehicle in a local coordinate system and a plurality of coordinates of points of a part of the object in the local coordinate system on the basis of the peripheral information and the movement information. A position estimation unit estimates a correlation between the parking lot coordinate system and the local coordinate system on the basis of the parking lot point group and the local peripheral information, and estimates the position of the vehicle in the parking lot coordinate system from the position of the vehicle in the local coordinate system and the correlation.