Abstract: Disclosed herein are a vehicle thermal runaway warning method, device, electronic equipment and readable storage medium. The method of vehicle thermal runaway warning includes obtaining operating data of a vehicle, the operating data including a plurality of cell voltage data of a battery pack in the vehicle, and dividing time windows for the plurality of cell voltage data according to a collection timing of the operating data. The method also includes extracting cell voltage characteristics from a partial cell voltage data corresponding to each of the divided time windows. The method further includes, in response to each cell voltage characteristic meeting a preset voltage warning condition, determining that the vehicle has a risk of thermal runaway, and controlling the vehicle to output thermal runaway warning information.

Abstract: Disclosed herein are a method and a device for remotely diagnosing vehicle faults, a vehicle and a computer storage medium. The method includes monitoring vehicle data uploaded by the vehicle in real time via a cloud platform, and determining whether to identify a preset fault abnormal signal identification from target data of the vehicle data. The method also includes, in response to the fault abnormal signal identification being identified from the target data, sending a fault diagnosis task to the vehicle according to the target data, and receiving diagnosis result data returned by the vehicle after the fault diagnosis task is executed locally by the vehicle. The method further includes generating a remote fault diagnosis result of the vehicle according to the vehicle data and the diagnosis result data.

Abstract: An area extraction method includes acquiring a captured image, generating a feature map using the captured image, extracting a candidate bounding box indicating an area in which an object exists in the captured image using the feature map, a segmentation step of generating a mask that is a bounding box indicating the area in which the object exists using the feature map and the candidate bounding box, acquiring input information which is input by a user regarding the object in the captured image, extracting the candidate bounding box using the feature map and the input information, and updating the feature map using the candidate bounding box extracted in the area estimation step and the input information. Wherein the candidate bounding box can be extracted further using the mask generated in the segmentation step, and the feature map can be updated using the mask generated in the segmentation step.

Abstract: Disclosed are a method and a device for predicting state of health of a battery, an electronic equipment and a readable storage medium. The method includes: obtaining battery data of a vehicle; performing feature extraction on the battery data to obtain a vehicle-using behavior feature corresponding to the vehicle; predicting and obtaining a predicted vehicle-using behavior feature of the vehicle in a next time step according to the vehicle-using behavior feature; and predicting and obtaining a health degree of the battery in the vehicle according to the predicted vehicle-using behavior feature and a battery health state prediction model.

Abstract: Disclosed are a consistency evaluation method for a vehicle battery cell, a device, an equipment, and a storage medium. The method includes: acquiring vehicle operation data, and selecting effective cell data in the vehicle operation data according to a preset effective data standard; processing the effective cell data according to a preset cell consistency index processing method to obtain cell consistency index data; determining a total index deviation value of all battery cells in the current vehicle according to the cell consistency index data; and if the total index deviation value exceeds a preset deviation threshold, determining a consistency risk of the current vehicle.

Abstract: Provided are: an amodal segmentation unit that generates a set of first amodal masks indicating a probability that a particular pixel belongs to a relevant object for each of objects, with respect to an input image in which a plurality of the objects partially overlap; an overlap segmentation unit that generates an overlap mask corresponding only to an overlap region where the plurality of objects overlap in the input image based on an aggregate mask obtained by combining the set of first amodal masks generated for each of the objects and a feature map generated based on the input image; and an amodal mask correction unit that generates and outputs a second amodal mask, which includes an annotation label indicating a category of each of the objects corresponding to a relevant pixel, for each of pixels in the input image using the overlap mask and the aggregate mask.

Abstract: In a current image processing environment, providing feedback for a user operation is slow, and a user cannot confirm the result of the operation in real time. Thus, the user interrupts the operation every time the user confirms the feedback, and a time period for performing image processing is long. An image processing device includes a guidance information generator. The guidance information generator acquires trajectory information to be used to segment an image object on an image input from a user, generates guidance information indicating a segmentation region desired by the user based on the trajectory information, and presents the segmentation region based on a user's intention in real-time. The guidance information generator provides a function of smoothly continuously segmenting an image object.

Abstract: Provided are: an amodal segmentation unit that generates a set of first amodal masks indicating a probability that a particular pixel belongs to a relevant object for each of objects, with respect to an input image in which a plurality of the objects partially overlap; an overlap segmentation unit that generates an overlap mask corresponding only to an overlap region where the plurality of objects overlap in the input image based on an aggregate mask obtained by combining the set of first amodal masks generated for each of the objects and a feature map generated based on the input image; and an amodal mask correction unit that generates and outputs a second amodal mask, which includes an annotation label indicating a category of each of the objects corresponding to a relevant pixel, for each of pixels in the input image using the overlap mask and the aggregate mask.

Abstract: In a current image processing environment, providing feedback for a user operation is slow, and a user cannot confirm the result of the operation in real time. Thus, the user interrupts the operation every time the user confirms the feedback, and a time period for performing image processing is long. An image processing device includes a guidance information generator. The guidance information generator acquires trajectory information to be used to segment an image object on an image input from a user, generates guidance information indicating a segmentation region desired by the user based on the trajectory information, and presents the segmentation region based on a user's intention in real-time. The guidance information generator provides a function of smoothly continuously segmenting an image object.