16results about How to "Save computing power" patented technology

Embodiments of the present application relate to the technical field of human-computer interaction, and disclose a method and device for determining an interactive gesture and an electronic device. The method comprises the following steps: first, target component detection is performed; then, gesture detection and recognition are performed in a local area (around a boundary box) near the target component. In addition, for N gesture detection boxes (multiple users) in a current video frame, M target gesture detection boxes are selected therefrom to perform hand component positioning and gesture recognition processing, which can reduce detection time consumption and improve real-time performance. On this basis, the interactive gesture is determined according to the gesture detection result of the current video frame and the gesture detection results of a plurality of historical video frames, that is, gesture recognition is selectively performed on the user in each frame in a plurality of continuous video frames to determine the interactive gesture, which can reduce the computing power, reduce the time consumption, improve the real-time performance, and improve the accuracy and stability of the interactive gesture. That is, in the multi-user human-computer interaction scene, the interactive gesture can be accurately and timely determined.

This application provides a license plate recognition method, apparatus, electronic device, and storage medium. The method includes: sliding a sliding window of preset length and width along the long side of a preset sliding area in a first image, acquiring multiple sliding window results generated during the sliding process; determining the cutting position of the image to be processed based on the multiple sliding window results and the cutting position; determining whether the license plate to be recognized is a double-layer license plate based on the cutting position; if the license plate to be recognized is a double-layer license plate, cutting and stitching the image to be processed according to the cutting position to obtain a second image; and inputting the second image into a license plate recognition model to obtain a first recognition result. In this technical solution, the electronic device only needs to store a single-layer license plate recognition model to simultaneously recognize both single-layer and double-layer license plates, improving memory utilization and reducing the computing power used.

This application discloses a method and apparatus for edge location detection, a self-moving device, a storage medium, and a program product. The edge location detection method includes: performing at least one region update operation during the movement of the self-moving device to update the target region; if a target region update is detected, updating the target map information to the attribute information of each first location point; if, based on the target map information, it is determined that among the multiple first location points, at least one target location point's height information conforms to a preset height range, determining the edge location based on at least one target location point. This method can reduce the storage space occupied by the self-moving device's map storage during edge location identification.

The application relates to the technical field of icing prediction, in particular to an icing weather time series prediction method and system based on a space-time generation network. The method comprises the following steps: an airborne terminal receives in-situ data; the airborne terminal performs a light compression and packaging operation on the in-situ data to generate a light file, and sends the light file to a ground terminal; wherein the following steps are included: denoising processing is performed on the in-situ data to obtain denoised data; the denoised data is compressed by using a target compression scale to make a light file; the ground terminal receives non-in-situ data; the ground terminal predicts a first icing probability of an airplane in a future period of time by using the non-in-situ data and the light file through a time series prediction model; and the ground terminal sends the icing probability to the airborne terminal. The application can greatly reduce the data fusion difficulty of a model input end.

This application provides a charging device, a charging cloud platform, and a charging system. The charging device includes a temperature controller and a temperature sensor. The temperature sensor detects the temperature of the charging device, and the temperature controller adjusts the temperature of the charging device. The charging device is used to: transmit temperature control data during the output of DC power, including the temperature from the temperature sensor and the corresponding rotational speed of the temperature controller; receive an empirical temperature control curve, which is a curve showing the relationship between the temperature of the charging device and the rotational speed of the temperature controller. The empirical temperature control curve is fitted based on temperature control data from at least two charging devices, including the charging device itself and other charging devices besides the charging device; and control the rotational speed of the temperature controller based on the empirical temperature control curve and the temperature from the temperature sensor. The solution provided in this application can reduce the R&D investment in temperature control characteristics, thereby reducing economic and labor costs.

The present application relates to a kind of signal wave direction and modulation pattern combined intelligent estimation model construction method, belong to signal analysis processing technical field, solve the existing technology in the wave direction estimation and modulation pattern identification, there is the problems of algorithm complexity, high hardware cost etc..The present application is by constructing multi-task deep neural network structure, and collecting multiple synchronous sampling IQ data stream, forms training sample and test sample, trains neural network structure, and increases modulation pattern and wave direction estimation extraction module, obtains wave direction and modulation pattern combined intelligent estimation model, then estimates test sample, obtains wave direction estimation result and modulation pattern identification result, completes the construction of model.Realize with less performance loss while realizing higher precision wave direction estimation and higher accuracy modulation pattern identification, it is favorable to reduce the workload required for the correlation of two kinds of results, while the demand for processing equipment algorithm can be reduced.

This invention discloses a low-light image enhancement method based on random region concealment and reconstruction. The network consists of two stages. In the first stage, the network is trained on a well-lit image dataset to reconstruct the noisy image after random regions are concealed, resulting in a denoising and reconstruction feature encoder for low-light noisy images. In the second stage, the network inherits the feature encoder model parameters from the first stage and inputs the extracted different features into a multi-scale feature fusion module guided by the reconstructed features. This allows the network to retain more image detail features while denoising. This invention utilizes a richer dataset of well-lit images, saving time and manpower by capturing a large number of real paired low-light images for network training. By fusing features extracted from different feature encoders, the network can quickly adapt to real low-light images under complex lighting conditions, achieving good low-light enhancement and denoising effects.

The invention relates to computing (S101) an information content of a section of a current image of a series of images of a video signal, wherein the video signal has to be fed to an algorithm for computing and indicating a detection of an object in the video signal. If the computed information content of the section of the current image is less than a threshold (S103), the computing and indicating of the detection of an object of the section of at least the current image or of the current image and further images of the series of images is suppressed (S105).

The application relates to the technical field of intelligent household appliances, and discloses a cross-domain small sample object image classification method and device for an intelligent terminal, which comprises the following steps: obtaining an object image to be identified; processing the object image to be identified by using a feature extraction module to extract a basic feature vector; processing and fusing the basic feature vector by using a double Riemann manifold processing module to generate a comprehensive feature representation; outputting an object classification recognition result by processing based on the comprehensive feature representation through a classification layer; the feature extraction module, the double Riemann manifold processing module and the classification layer constitute a lightweight self-network model; the lightweight self-network model is obtained by removing a teacher network after joint training through topological relationship knowledge distillation and progressive self-training. The lightweight self-network obtained by the method is suitable for the low computing power and low storage requirement of an intelligent terminal edge end, can realize local low-delay and high-precision classification and recognition of an object image, and solves problems such as uneven illumination and domain offset in the intelligent terminal.

The present invention provides a multi-modal obstacle avoidance system for multi-sensor fusion of an unmanned ship based on ROS, which is characterized by including three parts: sensors, a controller, and an actuator. In this system, a lidar, an industrial camera, an inertial measurement unit, and a GPS module are used to sense the surrounding environment and obtain attitude and position information, belonging to the sensors of the system; an artificial intelligence development board and a single-chip microcomputer are the main control modules, which make decisions according to the input through built-in algorithms, belonging to the controller of the system; a drive controller and a drive mechanical device are used to execute the decisions of the controller, belonging to the actuator of the system; the present invention uses a multi-sensor distributed modular architecture, enabling various functions to be coupled together, allowing tasks to be executed simultaneously in multiple threads, greatly reducing computing power, making the control more flexible, and equipped with a high-efficiency and high-accuracy vision-lidar fusion obstacle avoidance algorithm, enabling the unmanned ship to flexibly handle various complex situations that occur on the water surface and having the capabilities of autonomous cruising and autonomous obstacle avoidance.

The present disclosure relates to a vehicle body roll swing control method, a controller, a vehicle and a storage medium. The vehicle body roll swing control method comprises: obtaining an excitation frequency of a vehicle running road surface; determining a target preset frequency band corresponding to the excitation frequency, and a target preset corresponding relationship corresponding to the target preset frequency band, wherein the target preset corresponding relationship is a corresponding relationship between the excitation frequency of the road surface and the current of the shock absorber, different target preset frequency bands correspond to different target preset corresponding relationships; and adjusting the current of the shock absorber according to the excitation frequency and the target preset corresponding relationship to adjust the damping of the shock absorber. The technical solution provided by the present disclosure uses only the target preset corresponding relationship between the road surface excitation frequency and the current of the shock absorber to adjust the current of the shock absorber according to the road surface excitation frequency, realizes the control of the vehicle body swing and good vibration isolation performance, and the algorithm is simple and saves computing power.

The application relates to a method, system, device and storage medium based on a feature value deduction core mold, wherein the method comprises the following steps: acquiring core mold data information; under the condition that the spatial position information of the core mold is legal, classifying and identifying the core mold according to the core mold data information, and generating corresponding feature values; taking the feature values as classification marks, recording the number of each core mold and the component information of the first core mold under the same feature value; constructing a three-dimensional body of the core mold according to the component information of the first core mold under the same feature value, and performing batch deduction calculation on the core mold through a self-defined algorithm according to the core mold type. Through the application, the problem that the core mold is calculated by being deducted one by one and the calculation is slow is solved, and the calculation efficiency and the engineering output efficiency are improved.

The application relates to the field of animation, and particularly discloses an animation display method and device for a motion object, which comprises the following steps: in the case that the motion object enters a water body region, calculating the diving depth of the motion object according to diving position information of the motion object and water surface information of the water body region; obtaining a diving animation corresponding to the diving depth according to the corresponding relationship between depth data and depth animation, and playing the obtained diving animation. According to the method, the diving animation can be quickly determined directly according to the diving depth, and complex calculation by means of a physical engine is not needed, so that the fluency of animation playing can be improved under the condition of saving computing power and reducing system resource consumption.

The application discloses a kind of automatic wharf horizontal transport equipment dirty detection method and device, construct first level convolutional neural network for detecting IGV from image and second level convolutional neural network for detecting dirty area from IGV, first level convolutional neural network and second level convolutional neural network are constructed into double-branch cascade detection model, the original image obtained from the automatic wharf operation scene is input as the double-branch cascade detection model, and the first level convolutional neural network identifies IGV from complex scene, and outputs the image labeled IGV boundary box, according to the boundary box, IGV subgraph containing only IGV image is cut out from image, so as to remove background interference and transmit to second level convolutional neural network, and second level convolutional neural network focuses on detecting dirty area from IGV subgraph, so as to improve the detection efficiency and detection precision of IGV dirty area.

The present application relates to livestock state monitoring technical field, especially in kind of livestock outlier detection method, electronic equipment and computer storage medium, including the following steps: S1. Construct data set; S2. Use target detection tool to carry out object detection to each picture in data set, draw the position mark of each livestock; S3. The position mark of all pictures in data set is superimposed in position, and the hotspot map is drawn;S4. According to the position mark in picture, the distance value of each livestock and the density score value of each livestock are calculated;S5. If the distance value and the density score value of certain livestock meet the outlier condition, the livestock is regarded as outlier;S6. If the time of continuously finding the livestock regarded as outlier exceeds time threshold, it is determined that there is livestock outlier in the fence;The present application does not need to be matched with identity tag, identification and tracking technology, and the calculation amount is small, fully considers space density, resource distribution, group activity mode, individual difference and other factors, and the outlier recognition precision and efficiency are significantly improved.