53results about How to "No need for manual labeling" patented technology

The invention discloses an obstacle recognition method and device for vehicles. The method in one specific embodiment comprises the steps of: acquiring point cloud data of a target area by using a laser radar sensor and acquiring image data of the target area by using an image acquisition device; recognizing obstacle information in the point cloud data by using a preset point cloud recognition model, and marking the recognition result to obtain a first marked result; recognizing obstacle information in the image data by using a preset image recognition model, and marking the recognition result to obtain a second marked result; comparing the first marked result with the second marked result to detect whether the both are same; and responding to the difference of the both, determining an accurate marked result in the first marked result and the second marked result, and outputting the accurate marked result. The method and the device realize quick and accurate recognition of the accurate marked result, do not need artificial marking in the whole course, and thus improve the marking efficiency.

The invention relates to a character element detection method in a natural scene image, belonging to the field of computers. This method first uses the maximum pooling operation to suppress the target non-maximally, then uses the feature extraction network to extract the feature, and finally integrates the top and bottom layer features through feature fusion to improve the representation ability of the feature and combine the prediction network to output the character target. exact location. By designing a novel neural network structure, the method of the invention can integrate the features of the top and bottom layers of characters in natural scene images, so as to realize accurate detection of the positions of characters arranged horizontally, obliquely and curvedly in a complex background.

The present application discloses a method for generating video summaries and related devices, which are applied to artificial intelligence machine learning technology. By acquiring the target video; then extracting the image features of each video frame to generate an image feature sequence; and dividing the video frame sequence into multiple target segment sequences to generate a paragraph feature sequence; combining the image feature sequence and the paragraph feature sequence Fusion to obtain fusion features; and then reinforcement learning training based on fusion features to generate video summaries. In this way, the unsupervised video summary generation process is realized. Due to the combination of image-level image features and depth-level paragraph features, the quality of video summary generation is guaranteed, and the unsupervised video summary generation process does not require manual annotation, thereby improving Video summary Generated efficiency and accuracy.

A technical scheme of the invention discloses a method for obtaining a text classifier used for automatic corpus tagging, and the text classifier. The method comprises: determining a concept set, using a concept keyword corresponding to each concept to match a non-tagging corpus text and perform automatic tagging processing, the concept keyword being in a concept keyword set; for each concept, when the number of texts in a tagging corpus text set corresponding to the concept meets a threshold condition, training a corresponding text classification model for the concept, to obtain a corresponding text classifier, and finally a text classifier set corresponding to the concept is obtained, all text numbers meeting the threshold condition. The invention provides an algorithm structure having universality, and a classification system is flexibly changed, calculation time and resources are saved. The text classifier just needs few initial corpus texts, and the text classifier automatically tags without manual tagging, so as to further save time and cost.

One embodiment of the invention provides an audio data processing method. The audio data processing method includes the steps: acquiring a spectrum corresponding to audio data; dividing the spectrum corresponding to the audio data into a homophonic tone spectrum and a non-homophonic tone spectrum, wherein the frequency in the homophonic tone spectrum is an integer multiple of the frequency of thefundamental tone; and determining the emotional information expressed by the audio data according to the characteristic information of the homophonic tone spectrum and the characteristic information of the non-homophonic tone spectrum. The audio data processing method can accurately identify the emotion expressed by the audio so as to enable a user to search the related audio of expressing the corresponding emotion according to the emotion dimension so as to bring a better experience for the user, by dividing the spectrum corresponding to the audio data into the homophonic tone spectrum and the non-homophonic tone spectrum, and determining the emotion information expressed by the audio data according to the characteristic information of the homophonic tone spectrum and the characteristic information of the non-homophonic tone spectrum. Besides, the embodiment of the invention provides an audio data processing device, a medium and a computing device.