Abstract: A method for determining a collision distance includes receiving a series of data points from a second vehicle that were during the second vehicle driving on a historical path, the data points contain path information and steering wheel angle, the path information contains position information; determining whether the first vehicle is located within a preset area range corresponding to the second vehicle using a series of positions of the second vehicle and the current position of the first vehicle; if the first vehicle is currently located within the preset area range, determining a lane change state of the second vehicle in the historical path according to the steering wheel angle, the lane change state represents the second vehicle changing lanes; and determining the collision distance between the vehicles according to the lane change state, the current position of the first vehicle, and the series of data points.

Abstract: The present disclosure relates to method, storage medium and electronic device for detecting vehicle crashes. The method comprises: acquiring state information of a target vehicle; and determining an event type of the target vehicle according to the state information and a trained convolutional neural network, the event type being any of the following types: a crash event, a near crash event and a baseline event. The event type of the vehicle is determined using the trained convolutional neural network in the present disclosure, so that the accuracy is high; and near crash events can be detected, thus, when a near crash event is detected, the driver can be further alerted or an evading operation is directly performed on the vehicle, so that the safety is improved and the safety of the driver and passengers is guaranteed.

Abstract: The present disclosure relates to a vehicle tracking method, a computer readable storage medium, and an electronic device. The method includes: determining a predicted value of state information of a target tracking vehicle based on a sequential Kalman filtering model according to a most recently acquired tracking value of the state information of the target tracking vehicle, wherein the state information at least includes location information; obtaining a detected value of the state information of the target tracking vehicle; and in response to the obtained detected value, acquiring a new tracking value of the state information of the target tracking vehicle based on the sequential Kalman filtering model according to the detected value and the most recently determined predicted value. Through the above technical solution, the tracking value of the state information of the target tracking vehicle may be determined more accurately.

Abstract: The present disclosure relates to a target object detection method, a readable storage medium and an electronic device. The method is periodically executed and the method includes: identifying a target object based on first N frames of image data obtained within a current execution period, wherein N is a positive integer, and N is less than the total number of frames of image data that can be obtained within the current execution period; and if the target object is identified, tracking the target object based on the obtained image data within the remaining time period of the current execution period. In the above technical solution, when the target object is identified, the identified target object is tracked within the remaining time period of the current execution period, so that the data calculation amount can be effectively reduced.

Abstract: The present disclosure relates to a method, a computer readable storage medium and electronic equipment for analyzing driving behavior. The method comprises: acquiring image information in a running process of a target vehicle; acquiring time series data in the running process according to the image information; and acquiring a target driving behavior score for the running process according to the time series data.

Abstract: A method and an apparatus for vehicle position detection are provided. An image collecting device installed on a target vehicle is used to capture a region in front of the target vehicle at a current moment under a fixed viewing angle, to acquire a real image. Then, a virtual image under a preset viewing angle is generated based on the real image. The virtual image includes effective features of a side vehicle, and the side vehicle is accurately recognized based on the effective features, thereby determining position information of the side vehicle, so as to prevent accidents such as a collision between the target vehicle and the side vehicle.

Abstract: A method and an apparatus for detecting a road lane are provided. The method includes acquiring a current road image of a road around a vehicle and inputting the current road image into a deep learning model and detecting a road lane region in the current road image based on a result outputted from the deep learning model. The deep learning model includes a first model device and a second model device. The first model device includes at least one first model subdevice which includes a convolutional neural network and a first recurrent neural network, and the second model device includes at least one second model subdevice which includes a deconvolution neural network and a second recurrent neural network.

Abstract: A method, a device and an apparatus for planning a vehicle speed are provided. The method includes: determining initial planning speeds at a target path point and a reference path point based on curvature radiuses of a target front road and a reference front road, such that first and second lateral accelerations are not greater than a lateral acceleration threshold; and determining a target longitudinal acceleration and a target planning speed at the target path point based on the initial planning speeds at the target path point and the reference path point and a reference journey, such that the target longitudinal acceleration is in a defined range. Therefore, a vehicle can drive based on the target planning speed and the target longitudinal acceleration at the target path point, thereby avoiding drastic deceleration and lateral offset, improving driving safety of the vehicle and riding comfort and saving energy.

Abstract: The present disclosure provides a method and a device for detecting network intrusion. The method includes: obtaining a feature vector of a network flow to be detected; and detecting the feature vector using a deep neural network, and determining a network intrusion category of the network flow to be detected, in which the deep neural network is generated by training with training data, the training data includes feature vectors of normal samples and feature vectors of attack samples, the attack samples include original attack samples and generated attack samples by adding noise to the original attack samples. The method can improve an ability to identify unknown attacks and a normalization ability of known attacks.

Abstract: Provided is a method for generating target detection information, including detecting target objects around the vehicle by multiple different types of sensors, and determining the detection targets representing a same target object, detected by the different types of sensors, by spatial position and time tracing. With taking the target object as the detection result, the target detection information generated for the detection result includes a spatial matching confidence of the detection result in the current detection period, a time matching confidence of the detection result, and target detection information on each of the detection targets representing the detection result, collected by the sensor detecting the detection target in a dimension corresponding to the sensor.

Abstract: The present disclosure relates to method, storage medium and electronic device for detecting vehicle crashes. The method comprises: acquiring state information of a target vehicle; and determining an event type of the target vehicle according to the state information and a trained convolutional neural network, the event type being any of the following types: a crash event, a near crash event and a baseline event. The event type of the vehicle is determined using the trained convolutional neural network in the present disclosure, so that the accuracy is high; and near crash events can be detected, thus, when a near crash event is detected, the driver can be further alerted or an evading operation is directly performed on the vehicle, so that the safety is improved and the safety of the driver and passengers is guaranteed.

Abstract: A method for detecting a lane line is provided. The method includes: determining candidate lane line regions in a lane image by filtering the lane image; extracting center points for each candidate lane line region; obtaining a fitting curve of each candidate lane line region by performing curve fitting on the center points of each candidate lane line region; classifying the candidate lane line regions as rectilinear and curvilinear candidate lane line regions according to a slope angle of the fitting curve of each candidate lane line region; dividing the candidate lane line regions into groups based on the classifying result; and determining two groups, which meet a first predetermined condition, as target groups, and recognizing candidate lane line regions in the target groups as lane line regions. Besides, an apparatus and a device for detecting a lane line are further provided.

Abstract: A method, an apparatus and a device for detecting lane boundaries are provided. The method includes: obtaining a current image of a lane, and extracting brightness jump points in the image by filtering the image; filtering out noise points from the brightness jump points, and determining remaining brightness jump points as edge points to form groups of the edge points, where a connection line of edge points in the same group forms one edge line; recognizing edge lines of the lane boundaries from edge lines; and grouping the edge lines of the lane boundaries, and recognizing edge lines in each group as edge lines of one lane boundary. Based on the method, a calculation for detecting the lane boundaries is simpler, and calculation resources and time consumed in detecting the lane boundaries are reduced to detect the lane boundaries accurately and quickly.

Abstract: A method for detecting anomalies in time series, a computer readable storage medium and an electronic device. An example method comprises: obtaining current metrical data; obtaining a time series set corresponding to the current metrical data; for each time series in the time series set, judging whether a memory nerve cell used for recording the time series exists; activating the memory nerve cell when the existence of the memory nerve cell is judged; allocating a memory nerve cell to the time series so as to record the time series when the absence of the memory nerve cell is judged, and activating the allocated memory nerve cell; and determining whether the current metrical data is abnormal at least according to the activated memory nerve cells.

Abstract: A method, a device and an apparatus for planning a vehicle speed are provided. The method includes: determining initial planning speeds at a target path point and a reference path point based on curvature radiuses of a target front road and a reference front road, such that first and second lateral accelerations are not greater than a lateral acceleration threshold; and determining a target longitudinal acceleration and a target planning speed at the target path point based on the initial planning speeds at the target path point and the reference path point and a reference journey, such that the target longitudinal acceleration is in a defined range. Therefore, a vehicle can drive based on the target planning speed and the target longitudinal acceleration at the target path point, thereby avoiding drastic deceleration and lateral offset, improving driving safety of the vehicle and riding comfort and saving energy.

Abstract: The present disclosure provides a method and a device for detecting network intrusion. The method includes: obtaining a feature vector of a network flow to be detected; and detecting the feature vector using a deep neural network, and determining a network intrusion category of the network flow to be detected, in which the deep neural network is generated by training with training data, the training data includes feature vectors of normal samples and feature vectors of attack samples, the attack samples include original attack samples and generated attack samples by adding noise to the original attack samples. The method can improve an ability to identify unknown attacks and a normalization ability of known attacks.

Abstract: A method for detecting a target object in a blind area of a vehicle is provided by embodiments of the application. The method includes: acquiring at least one frame of an image generated by shooting a blind area of a vehicle by a shooting device; extracting an image feature of an area where at least one predetermined detection gate is located in the image; and matching the image feature of the area where the predetermined detection gate is located with a matching template of the predetermined detection gate to determine a target object. An apparatus for detecting a target object in a blind area of a vehicle is further provided by embodiments of the application.

Abstract: A system for securely entering particular information includes a mobile device and a background server. The mobile device includes a first area which is a non-secure environment, a second area which is a secure environment and a switching module implementing switchings between the first and second areas. At least one first application module for executing a business function application is provided in the first area. A second application module for executing a particular information entering application and an encryption module for encrypting entered particular information are provided in the second area. If a particular information entering is required by the first application module, the switching module triggers the second application module to perform the particular information entering, and returns, to the first application module, an encryption result obtained by encrypting the entered particular information.