Abstract: Embodiments of this disclosure provide a video frame interpolation apparatus and method. The method includes calculating a bidirectional optical flow between a first frame and a second frame; an performing kernel and weight estimation according to the first frame and the second frame. An adaptive local convolutional kernel is generated by using a convolutional layer and a weight coefficient is generated by using another convolutional layer. A conversion on the first frame and the second frame is performed by using an adaptive conversion layer according to the bidirectional optical flow, the weight coefficient and the adaptive local convolutional kernel, so as to generate a conversion frame. A frame synthesis on the first frame, the second frame and the conversion frame is performed to generate an interpolation frame between the first frame and the second frame.

Abstract: Embodiments of this disclosure provide a deep learning model used for image recognition and apparatus and method thereof. The model includes a determination layer configured to determine whether features in feature maps are features of positions where objects of attention are located, and different weights are granted for the positions where the objects of attention are located and other features in performing weight and composition processing on the features. Hence, the model may be guided to be focused on attention features and make correct determination, thereby improving performance and precision of the model.

Abstract: An apparatus for bonding and combining a pocket spring bed mesh and method, and a pocket spring bed mesh. The apparatus includes a rack, a platform arranged on the rack for driving the pocket spring bed mesh to move reciprocally, a rotating mechanism used for driving the pocket spring bed mesh to rotate, and a combining mechanism used for combining pocket spring strings to form the pocket spring bed mesh. The combining mechanism bonds and combines pocket spring strings to form an unshaped pocket spring bed mesh which is driven by the platform to move to the position of rotating mechanism to be rotated for adjusting the orientation, then the pocket spring bed mesh is moved by the platform to the combining mechanism, and the combining mechanism bonds and combines the side parts of the unshaped pocket spring bed mesh using a pocket spring string of a smaller diameter.

Abstract: Disclosed are a cushion conveying device and method, and a cushion rolling packaging apparatus and method. The cushion conveying device includes a frame (10), a conveying platform (20), a pressing mechanism (30) and a folding mechanism (40). At least one gap area is provided on the conveying platform (20). The pressing mechanism (30) is movable back and forth to contact and press at least one part of the cushion on the conveying platform (20). The folding mechanism (40) includes at least one folding member (41) movable back and forth to pass through the gap area, the folding member (41) is capable of extending out of the gap area to abut against the cushion on the conveying platform (20), so as to turn up and fold the cushion. The cushion, when conveyed to the conveying platform (20), is folded in an overturning mode by the pressing mechanism (30) and the folding mechanism (40) cooperatively, so that the folding action is simple and fast.

Abstract: The present invention concerns a spring core (1, la, 12, 13, 17, 18) that may be used in e.g. bed mattresses, chairs or sofas. The spring core (1, 1a, 12, 13, 17, 18) comprises springs placed inside pocket (3). The pockets (3) are placed in a number of rows, which rows of pockets (3) are placed side by side. The spring core (1, 1a, 12, 13, 17, 18) is held in a compressed state by means of at least one cord (5). The at least one cord (5) is formed into braids (6) at opposite outer ends (7) of each row of pockets (3). Further, the at least one cord (4) forms a number of loops (8) on at least one side of each row of pockets (3). By pulling at one free end (10) of the at least one cord (5) the braids (6) and loops (8) are dissolved, allowing the spring core (1) to return to the non-compressed state.

Abstract: Embodiments of this disclosure provide a training method, an image encoding method, an image decoding method and apparatuses thereof. The image encoding apparatus includes: an image encoder configured to encode input image data to obtain a latent variable; a quantizer configured to perform quantizing processing on the latent variable according to a quantization step to generate a quantized latent variable; and an entropy encoder configured to perform entropy coding on the quantized latent variable by using an entropy model to form a bit stream.

Abstract: A pocket spring string, a pocket spring mattress core and a mattress. The pocket spring string includes: springs; cloth, which is folded and provided with welds to form multiple adjacent pockets, each pocket being provided with an opening, and the springs being received in the pockets respectively; and thread provided to stitch the openings so that the springs are packaged in the pockets in a compressed state. The pocket spring mattress core is formed by connection of the pocket spring strings, and the mattress includes a mattress cover and the pocket spring mattress core. Because the top and/or bottom of each pocket is provided with the opening which is stitched by the thread, when the thread is removed, the springs can be quickly separated from the pockets, so that the metal material and the cloth are separated without any special technical means.

Abstract: Embodiments of this disclosure provide an arm action identification method and apparatus and an image processing device. A human body detection is performed on an image to obtain multiple key points of the human body in the image. An arm action is identified to be an upward action or a downward action by using a shoulder key point, an elbow key point and a wrist key point in the multiple key points. Arm actions indicative of upward, downward, or forward, actions may be identified based upon, for example, lifting, putting down, holding forward, actions, by using the key points of the human body, thereby achieving computer-level action identification, and lowering complexity of computation.

Abstract: Embodiments of this disclosure provide an image coding method and apparatus and an image compression system. The image coding apparatus includes a memory and a processor. The processor is configured to perform feature extraction on an input image to obtain feature maps of N channels; assign a weight to a feature map of each channel among the N channels; perform down-dimension processing on weighted feature maps processed in association with the N channels, to obtain feature maps of M channels and output the feature maps of M channels, M being smaller than N. Hence, by multiplying different feature maps by a weight to obtain corresponding importance and then performing down-dimension processing on the feature maps processed according to the weighting, time for decoding may be reduced.

Abstract: Embodiments of this disclosure provide a deep learning model used for driving behavior recognition and training apparatus and method thereof. In recognition, the model performs feature extraction by using a plurality of consecutive input images captured from a driving angle of view of a vehicle, and performs temporal and spatial fusion on extracted features by using a recursive neural network. In training, as images captured from a driving angle of view of a vehicle are acquired, the model may be trained. Hence, the model may accurately recognize various classes of driving behaviors.

Abstract: Embodiments of this disclosure provide a smoke detection method and apparatus. The apparatus includes a processor configured to detect foreground blobs in images of a plurality of frames in a video; determine motion areas of detected foreground blobs; determine a first degree of overlapping of the foreground blobs in images of at least two frames, and/or determine a second degree of overlapping of the foreground blobs and motion areas to which the foreground blobs correspond; determine interfering foreground blobs according to the first degree of overlapping and/or the second degree of overlapping; and extract features from motion areas of remaining foreground blobs with the interfering foreground blobs being removed, and detect smoke according to the features. With the embodiments of this disclosure, accuracy of smoke detection may be increased, and false detection resulted from such interfering objects as water blobs, or light spots, etc., may be avoided.

Abstract: Embodiments of this disclosure provide a video frame interpolation apparatus and method. The method includes calculating a bidirectional optical flow between a first frame and a second frame; an performing kernel and weight estimation according to the first frame and the second frame. An adaptive local convolutional kernel is generated by using a convolutional layer and a weight coefficient is generated by using another convolutional layer. A conversion on the first frame and the second frame is performed by using an adaptive conversion layer according to the bidirectional optical flow, the weight coefficient and the adaptive local convolutional kernel, so as to generate a conversion frame. A frame synthesis on the first frame, the second frame and the conversion frame is performed to generate an interpolation frame between the first frame and the second frame.

Abstract: Embodiments of this disclosure provide an image coding method and apparatus and an image decoding method and apparatus. The image coding method includes: performing feature extraction on to-be-processed image data by using a convolutional neural network, to generate feature maps of the image data; quantizing the feature maps to generate discrete feature maps; preprocessing the discrete feature maps to generate preprocessed data, an amount of data of the preprocessed data being less than an amount of data of the discrete feature maps; calculating probabilities of to-be-coded data in the discrete feature maps according to the preprocessed data; and performing entropy coding on the to-be-coded data according to the probabilities of the to-be-coded data.

Abstract: Embodiments of this disclosure provide a training method, an image encoding method, an image decoding method and apparatuses thereof. The image encoding apparatus includes: an image encoder configured to encode input image data to obtain a latent variable; a quantizer configured to perform quantizing processing on the latent variable according to a quantization step to generate a quantized latent variable; and an entropy encoder configured to perform entropy coding on the quantized latent variable by using an entropy model to form a bit stream.

Abstract: An inclined pocketed spring string (4) and a pocketed spring bed core (3). The inclined pocketed spring string (4) comprises a plurality of pocketed individual springs (1) connected at intervals. Each pocketed individual spring (1) comprises a fabric (11) and an individual spring (12) packaged in the fabric (11). The individual springs (12) in the pocketed spring string (4) are entirely or partially inclined in the fabrics (11) in an inclined manner. The inclined pocketed spring string (4) and the pocketed spring bed core (3) of the present invention, as compared with the pocketed spring bed core of the same size, can effectively decrease the number of springs used and reduce manufacturing costs.

Abstract: Embodiments of this disclosure provide a person searching method and apparatus and an image processing device. The method includes: performing person detection on a reference image, determining a query person, and acquiring property information on the query person; performing person detection on at least one video surveillance image, determining all candidate persons, and acquiring property information on all the candidate persons; calculating a match score of each candidate person according to the property information on the query person and property information on each candidate person, and selecting a predetermined number of candidate persons in a descending order of the match scores; and calculating similarities between the query person and the selected candidate persons, and taking a candidate person in the selected candidate persons having a highest similarity with the query person as the query person.

Abstract: A method and a device for augmenting data in a monitoring video are provided which includes: selecting randomly, based on a function to be implemented for the data and a parameter range which are set by a user or by default, one or more processing functions to be performed on the data and parameters of the processing functions; processing the data using the selected one or more processing functions, to obtain new data; and repeating the above processes until a required amount of data is generated. With the method, monitoring data having diversity and a small size can be obtained with only a few input samples, and a high degree of randomness and comprehensiveness of the augmented data can be achieved.

Abstract: Embodiments of this disclosure provide an action recognition method and apparatus and an electronic equipment. The action recognition apparatus includes: a key-point feature extracting unit configured to process information on key points in a target human body in an image frame, to calculate key-point features of the target human body, the key-point features including a position of a predetermined key point and an angle of a predetermined joint in the target human body; and a first recognizing unit configured to recognize an action of the target human body according to the key-point features, and output a first recognition result.

Abstract: Embodiments of this disclosure provide an arm action identification method and apparatus and an image processing device. A human body detection is performed on an image to obtain multiple key points of the human body in the image. An arm action is identified to be an upward action or a downward action by using a shoulder key point, an elbow key point and a wrist key point in the multiple key points. Arm actions indicative of upward, downward, or forward, actions may be identified based upon, for example, lifting, putting down, holding forward, actions, by using the key points of the human body, thereby achieving computer-level action identification, and lowering complexity of computation.

Abstract: Embodiments of this disclosure provide an image coding method and apparatus and an image compression system. The image coding apparatus includes a memory and a processor. The processor is configured to perform feature extraction on an input image to obtain feature maps of N channels; assign a weight to a feature map of each channel among the N channels; perform down-dimension processing on weighted feature maps processed in association with the N channels, to obtain feature maps of M channels and output the feature maps of M channels, M being smaller than N. Hence, by multiplying different feature maps by a weight to obtain corresponding importance and then performing down-dimension processing on the feature maps processed according to the weighting, time for decoding may be reduced.