Abstract: It is possible to estimate a slack level accurately in consideration of a shape of a deformed cable. A point cloud analysis device sets a plurality of regions of interest obtained by window-searching a wire model including a quadratic curve model representing a cable obtained from a point cloud consisting of three-dimensional points on an object, the region of interest being divided into a first region and a second region.

Abstract: Dense depth information can be generated using only a monocular image and sparse depth information.

Abstract: A mesh structure facility detection device detects data corresponding to a mesh structure facility from three-dimensional structure data representing a space including an outer shape of an object, and projects the three-dimensional structure data in a predetermined direction to obtain two-dimensional structure data; and detects a point included in a region in which the two-dimensional structure data has a density of more than or equal to a predetermined threshold value as a point corresponding to the mesh structure facility.

Abstract: A learning apparatus includes: a data generation unit that learns generation of data based on a class label signal and a noise signal; an unknown degree estimation unit that learns estimation of a degree to which input data is unknown using a training set and the data generated by the data generation unit; a first class likelihood estimation unit that learns estimation of a first likelihood of each class label for input data using the training set; a second class likelihood estimation unit that learns estimation of a second likelihood of each class label for input data using the training set and the data generated by the data generation unit; a class likelihood correction unit that generates a third likelihood by correcting the first likelihood on the basis of the unknown degree and the second likelihood; and a class label estimation unit that estimates a class label of data related to the third likelihood on the basis of the third likelihood, thereby automatically estimating a cause of an error by a deep mod

Abstract: An identification device acquires a plurality of identification target points by sampling a target point group that is a set of three-dimensional target points. The identification device calculates relative coordinates of a neighboring point of the identification target point with respect to the identification target point. The identification device inputs coordinates of the plurality of identification target points and relative coordinates of neighboring points with respect to each of the plurality of identification target points into a class label assigning learned model to acquire class labels of the plurality of identification target points and validity of the class labels with respect to the neighboring points for each of the plurality of identification target points.

Abstract: Simultaneous learning of a plurality of different tasks and domains, with low costs and high precision, is enabled. A learning unit 160, on the basis of learning data, uses a target encoder that takes data of a target domain as input and outputs a target feature expression, a source encoder that takes data of a source domain as input and outputs a source feature expression, a common encoder that takes data of the target domain or the source domain as input and outputs a common feature expression, a target decoder that takes output of the target encoder and the common encoder as input and outputs a result of executing a task with regard to data of the target domain, and a source decoder that takes output of the source encoder and the common encoder as input and outputs a result of executing a task with regard to data of the source domain, to learn so that the output of the target decoder matches training data, and the output of the source decoder matches training data.

Abstract: Annotation can be easily performed on a three-dimensional point cloud and a working time can be reduced. An interface unit 22 displays a point cloud indicating a three-dimensional point on an object, and receives designation of a three-dimensional point indicating an annotation target object and designation of a three-dimensional point not indicating the annotation target object. A candidate cluster calculation unit 32 calculates a value of a predetermined evaluation function indicating a likelihood of a point cloud cluster being the annotation target object based on the designation of a three-dimensional point for point cloud clusters obtained by clustering the point clouds. A cluster selection and storage designation unit 34 causes the interface unit 22 to display the point cloud clusters in descending order of the value of the evaluation function, and receives a selection of a point cloud cluster to be annotated.

Abstract: A training unit 24 performs leaning of a recognizer that recognizes labels of data based on a plurality of training data to which training labels are given. A score calculation unit 28 calculates a score output by the recognizer for each of the plurality of training data by using the trained recognizer. A threshold value determination unit 30 determines a threshold value for the score for determining the label, based on a shape of an ROC curve representing a correspondence between a true positive rate and a false positive rate, which is obtained based on the score calculated for each of the plurality of training data. A selection unit 32 selects the training data difficult to recognize by the recognizer based on the threshold value determined and the score calculated for each of the plurality of training data. The process of each unit described above is repeated until a predetermined iteration termination condition is satisfied.

Abstract: A candidate detection unit 118 detects, for each of a plurality of target images, candidate regions representing a specific detection target region using a discriminator. A region-label acquisition unit 120 acquires, for a part of the target images, position information of a search region as a teacher label. A region specifying unit 121 imparts, based on the part of the target images and the acquired position information of the search region, the position information of the search region to each of the target images, which are not the part of the target images, in semi-supervised learning processing. A filtering unit 122 outputs, for each of the acquired plurality of target images, among the candidate regions, a candidate region, an overlapping degree of which with the search region is equal to or larger than a fixed threshold.

Abstract: A class label of a three-dimensional point cloud can be identified with high performance. The key point choice unit 22 extracts a key point cloud 35 including three-dimensional points efficiently representing features of an object and a non-key point cloud 37. A inference unit 24 takes, as representative points, a plurality of points selected by down-sampling from each of the key point cloud 35 and the non-key point cloud 37, extracts, with respect to each of the representative points, a feature of each representative point from coordinates and the feature of the representative point and coordinates and features of neighboring points positioned near the representative point.

Abstract: A clustering unit (101) divides an input three-dimensional point cloud into a plurality of clusters and outputs cluster data, a surrounding point sampling unit (102) extracts, for each of the plurality of clusters, a surrounding three-dimensional point cloud present within a predetermined distance of the cluster based on the three-dimensional point cloud and the cluster data, a learning unit (103) receives, as inputs, extended cluster data including information on a three-dimensional point cloud included in each cluster obtained by the division and information on the extracted surrounding three-dimensional point cloud and a correct answer label indicative of an object to which the three-dimensional point cloud included in each cluster belongs, and learns a parameter of a DNN for estimating a label of each cluster from the extended cluster data, and an estimation unit (104) inputs the extended cluster data related to the cluster of which the label is unknown to the DNN of which the parameter is trained to esti

Abstract: A data selection method selects, based on a set of labeled first data pieces and a set of unlabeled second data pieces, a target to be labeled from the set of the second data pieces. The method includes: a classification procedure classifying data pieces belonging to the set of the first data pieces and data pieces belonging to the set of the second data pieces into clusters of the number at least one more than the number of types of the labels; and a selection procedure selecting the second data piece to be labeled from a cluster, from among the clusters, that does not include the first data piece, each of the procedures being performed by a computer. Thereby, it is possible to select the data piece to be labeled, which is effective for a target task, from among data sets of unlabeled data pieces.

Abstract: A point group including a small number of points that have been assigned labels is taken as an input to assign labels to points that have not been assigned labels.

Abstract: A mesh structure facility detection device that detects data corresponding to a mesh structure facility from three-dimensional structure data representing a space including an outer shape of an object, includes: a projection unit that projects the three-dimensional structure data in a predetermined direction to obtain two-dimensional structure data; and a detection unit that detects a point included in a region in which the two-dimensional structure data has a density of more than or equal to a predetermined threshold value as a point corresponding to the mesh structure facility.

Abstract: It is possible to estimate a slack level accurately in consideration of a shape of a deformed cable. A point cloud analysis device sets a plurality of regions of interest obtained by window-searching a wire model including a quadratic curve model representing a cable obtained from a point cloud consisting of three-dimensional points on an object, the region of interest being divided into a first region and a second region.

Abstract: A three-dimensional point cloud label learning and estimation device includes: a clustering unit that clusters a three-dimensional point cloud into clusters; a learning unit that makes a neural network learn to estimate a label corresponding to an object to which points contained in each of the clusters belong; and an estimation unit that estimates a label for the cluster using the neural network learned at the learning unit. In the three-dimensional point cloud label learning and estimation device, the neural network uses a total sum of sigmoid function values (sum of sigmoid) when performing feature extraction on the cluster.

Abstract: Provided is a point cloud analysis device that curbs a decrease in model estimation accuracy due to a laser measurement point cloud. A clustering unit (30) clusters a point cloud representing a three-dimensional point on an object obtained by a measurement unit mounted on a moving body and performing measurement while scanning a measurement position, within a scan line, to obtain a point cloud cluster. A central axis direction estimation unit (32) estimates a central axis direction based on the point cloud cluster. A direction-dependent local effective length estimation unit (34) estimates a local effective length based on an estimated central axis direction and an interval of scan lines, the local effective length being a length when a length of projection of the point cloud cluster in a central axis direction for each of the point cloud clusters is interpolated by an amount of a loss part of the point cloud.

Abstract: Dense depth information can be generated using only a monocular image and sparse depth information.

Abstract: Labels can be accurately identified even for an image with a resolution not used in training data. Based on an input image, a resolution of the input image, and a resolution of a training image used for training a trained model of assigning labels to pixels of an image, a plurality of low-resolution images are generated from the input image by using a plurality of shift amounts for a pixel correspondence between the input image and the respective low-resolution images with a resolution corresponding to the training image, the low-resolution images are input to the trained model, a plurality of low-resolution label images is output in which pixels of the respective low-resolution images are assigned labels, and a label image is output in which labels for pixels of the input image are obtained, based on the shift amounts used for generating the low-resolution images and the low-resolution label images.

Abstract: A robot system includes circuitry. The circuitry may be configured to acquire teaching position data including a plurality of teaching positions arranged in time series based on the demonstration data of the operator. The circuitry may be further configured to generate thinned position data obtained by removing at least one of the teaching positions from the teaching position data. The circuitry may be further configured to generate a position command based on the thinned position data. The circuitry may be further configured to operate the work robot based on the position command.