Abstract: Provided are a method and system for automatic driving data collection and closed-loop management. The method includes: obtaining vehicle driving data; preprocessing the vehicle driving data; obtaining incremental data by filtering, through a pre-trained neural network based on a predetermined filtering rule, the preprocessed vehicle driving data; and storing the incremental data or transmitting the incremental data to a cloud. The method can effectively filter high-value incremental data, thereby reducing requirements for data storage volume and/or data transmission bandwidth of the system. The system of the present disclosure can be post-mounted or pre-mounted on a vehicle, and is independent of specific vehicle type of the vehicle. In addition, it is not necessary for the vehicle to be equipped with real-value systems such as high-cost laser radars, which greatly improves use convenience of the system and facilitates rapid and large-scale application.

Abstract: Provided are a method and system for automatic driving data collection and closed-loop management. The method includes: obtaining vehicle driving data; preprocessing the vehicle driving data; obtaining incremental data by filtering, through a pre-trained neural network based on a predetermined filtering rule, the preprocessed vehicle driving data; and storing the incremental data or transmitting the incremental data to a cloud. The method can effectively filter high-value incremental data, thereby reducing requirements for data storage volume and/or data transmission bandwidth of the system. The system of the present disclosure can be post-mounted or pre-mounted on a vehicle, and is independent of specific vehicle type of the vehicle. In addition, it is not necessary for the vehicle to be equipped with real-value systems such as high-cost laser radars, which greatly improves use convenience of the system and facilitates rapid and large-scale application.

Abstract: A system includes a computer including a processor and a memory, the memory storing instructions executable by the processor to determine respective threat numbers for each of a plurality of targets based on an angular acceleration of a host vehicle and actuate a component in the host vehicle based on the threat numbers.

Abstract: The present disclosure provides an electronic device, a method for constructing a scoring model of retail outlets, a system and a computer readable medium. The method includes: crawling POI data of a predetermined map website by a crawler system; acquiring surrounding POI data based on a location of each retail outlet, and constructing POI relevant outlet features based on the surrounding POI data; acquiring surrounding LBS information based on the location of each retail outlet, and constructing client relevant features based on the surrounding LBS information; scoring each retail outlet based on a number of new clients increased in a predetermined time period and a revenue index; and constructing the scoring model by performing supervised learning of a preset classification algorithm model using the POI relevant outlet feature, the client relevant feature, and a score of the retail outlet.

Abstract: A distance offset is determined based on a determined time to collision, a relative lateral distance, and a relative longitudinal distance between the target and a host vehicle. A threat estimation is determined based on the distance offset and a distance threshold. A component of the host vehicle are actuated based on the threat estimation.

Abstract: A system includes a computer including a processor and a memory, the memory storing instructions executable by the processor to determine respective threat numbers for each of a plurality of targets based on an angular acceleration of a host vehicle and actuate a component in the host vehicle based on the threat numbers.

Abstract: A respective confidence level of a potential collision is determined for each of a plurality of targets based on each target's heading angle and distance from a host vehicle. A threat number is determined for each target when its respective confidence level is above a threshold. A vehicle component is actuated based on the threat number.

Abstract: A plurality of targets are identified. A path for each target is predicted. A threat number for each target is determined based at least in part on the predicted paths. The threat number indicates a probability of a collision between the respective target and a host vehicle. One or more vehicle subsystems in the host vehicle is actuated based on the threat numbers.

Abstract: A time to collision is determined between a turning host vehicle and each of a plurality of targets. Based on a lateral distance and a longitudinal distance, a minimum distance is determined between the turning host vehicle and each of the plurality of targets. A threat number is determined for each target selected based on the time to collision and the minimum distance. A vehicle component is actuated based on the threat number.

Abstract: A controller in a host vehicle includes a processor and a memory storing processor-executable instructions. The processor is programmed to calculate an error bound for confidence intervals of a predicted position at a future time of a target vehicle relative laterally to a current position and orientation of the host vehicle at a current time based on a current position and velocity of the target vehicle and the future time.

Abstract: A time to collision is determined between a turning host vehicle and each of a plurality of targets. Based on a lateral distance and a longitudinal distance, a minimum distance is determined between the turning host vehicle and each of the plurality of targets. A threat number is determined for each target selected based on the time to collision and the minimum distance. A vehicle component is actuated based on the threat number.

Abstract: A distance offset is determined based on a determined time to collision, a relative lateral distance, and a relative longitudinal distance between the target and a host vehicle. A threat estimation is determined based on the distance offset and a distance threshold. A component of the host vehicle are actuated based on the threat estimation.

Abstract: A respective confidence level of a potential collision is determined for each of a plurality of targets based on each target's heading angle and distance from a host vehicle. A threat number is determined for each target when its respective confidence level is above a threshold. A vehicle component is actuated based on the threat number.

Abstract: A controller includes a processor and a memory storing processor-executable instructions in a host vehicle. The processor is programmed to designate a target vehicle as a collision risk upon determining that an intersection angle between the host vehicle and the target vehicle is between preset lower and upper bounds and an absolute value of an azimuth angle rate of change of the host vehicle is below a preset threshold.

Abstract: A controller includes a processor and a memory storing processor-executable instructions in a host vehicle. The processor is programmed to designate a target vehicle as a collision risk upon determining that an intersection angle between the host vehicle and the target vehicle is between preset lower and upper bounds and an absolute value of an azimuth angle rate of change of the host vehicle is below a preset threshold.

Abstract: A controller in a host vehicle includes a processor and a memory storing processor-executable instructions. The processor is programmed to calculate an error bound for confidence intervals of a predicted position at a future time of a target vehicle relative laterally to a current position and orientation of the host vehicle at a current time based on a current position and velocity of the target vehicle and the future time.

Abstract: A plurality of targets are identified. A path for each target is predicted. A threat number for each target is determined based at least in part on the predicted paths. The threat number indicates a probability of a collision between the respective target and a host vehicle. One or more vehicle subsystems in the host vehicle is actuated based on the threat numbers.

Abstract: Systems, methods, and media for detecting an anatomical object in a medical device image are provided. In some embodiments, system for detecting an anatomical object in a medical device image are provided, the systems comprising: at least one hardware processor that: applies the medical device image to a classifier having a plurality of stages, wherein a first stage of the plurality of stages and a second stage of the plurality of stages each includes a strong learner formed from a plurality of weak learners, and the weak learners in the second stage include a plurality of the weak learners included in the first stage; and identifies the medical device image as being positive or negative of showing the anatomical object based on the application the medical device image to be classifier.

Abstract: An intersection of a host vehicle and a target vehicle is identified. Data relating to the target vehicle are collected. A map of a surrounding environment is developed. A driver intent probability is determined based at least in part on the map. A threat estimation is determined based at least in part on the driver intent probability. At least one of a plurality of safety systems is activated based at least in part on the threat estimation.

Abstract: An intersection of a host vehicle and a target vehicle is identified. Data relating to the target vehicle are collected. A map of a surrounding environment is developed. A driver intent probability is determined based at least in part on the map. A threat estimation is determined based at least in part on the driver intent probability. At least one of a plurality of safety systems is activated based at least in part on the threat estimation.