Disclosed are methods and devices related to autonomous driving. In one aspect, a method is disclosed. The method includes determining three-dimensional bounding indicators for one or more first objects in road target information captured by a light detection and ranging (LIDAR) sensor; determining camera bounding indicators for one or more second objects in road image information captured by a camera sensor; processing the road image information to generate a camera matrix; determining projected bounding indicators from the camera matrix and the three-dimensional bounding indicators; determining, from the projected bounding indicators and the camera bounding indicators, associations between the one or more first objects and the one or more second objects to generate combined target information; and applying, by the autonomous driving system, the combined target information to produce a vehicle control signal.

A deep multimodal cross-layer intersecting fusion method, a terminal device and a storage medium are provided. The method includes: acquiring an RGB image and point cloud data containing lane lines, and pre-processing the RGB image and point cloud data; and inputting the pre-processed RGB image and point cloud data into a pre-constructed and trained semantic segmentation model, and outputting an image segmentation result. The semantic segmentation model is configured to implement cross-layer intersecting fusion of the RGB image and point cloud data. In the new method, a feature of a current layer of a current modality is fused with features of all subsequent layers of another modality, such that not only can similar or proximate features be fused, but also dissimilar or non-proximate features can be fused, thereby achieving full and comprehensive fusion of features. All fusion connections are controlled by a learnable parameter.

Methods for predicting a yield of fruit growing in an agricultural plot are provided. At a first time, a first plurality of images of a canopy of the agricultural plot is obtained from an aerial view of the canopy of the agricultural plot. From the first plurality of images, a first number of detectable fruit is estimated. At a second time, a second plurality of images of the canopy of the agricultural plot is obtained from the aerial view of the canopy of the agricultural plot. From the second plurality of images, a second number of detectable fruit is estimated. Using at least the first number of detectable fruit and the second number of detectable fruit and agricultural plot information, predict the yield of fruit from the agricultural plot.

A computer system obtains, using a camera, a first plurality of images of a canopy an agricultural plot. For each respective fruit of a plurality of fruit growing in the agricultural plot, the computer system identifies a first respective image in the first plurality of images that comprises the respective fruit. The first respective image has a corresponding first camera location. The computer system also identifies a second respective image in the first plurality of images that comprises the respective fruit. The second respective image has a corresponding second camera location. The computer system uses at least i) the first and second respective images and ii) a distance between the first and second camera locations to determine a corresponding size of the respective fruit.

A computer system obtains, in electronic format, a training dataset. The training dataset comprises a plurality of training images from a plurality of agricultural plots. Each training image is from a respective agricultural plot in the plurality of agricultural plots and comprises at least one identified fruit. The computer system determines, for each respective fruit in each respective training image in the plurality of training images, a corresponding contour. The computer system trains an untrained or partially trained computational model using at least the corresponding contour for each respective fruit in each respective training image in the plurality of training images, thereby obtaining a first trained computational model that is configured to identify fruit in agricultural plot images.

Systems and methods for generating semantic occupancy maps are provided. In particular, a computing system can obtain map data for a geographic area and sensor data obtained by the autonomous vehicle. The computer system can identify feature data included in the map data and sensor data. The computer system can, for a respective semantic object type from a plurality of semantic object types, determine, by the computing system and using feature data as input to a respective machine-learned model from a plurality of machine-learned models, one or more occupancy maps for one or more timesteps in the future, and wherein the respective machine-learned model is trained to determine occupancy for the respective semantic object type. The computer system can select a trajectory for the autonomous vehicle based on a plurality of occupancy maps associated with the plurality of semantic object types.

A scene model constructing method includes the following steps. According to multiple position parameters in multiple scene materials, classifying the scene materials into multiple position groups. According to scene similarities between the scene materials, classifying the scene materials into multiple first similar image sub-groups and multiple second similar image sub-groups. Establishing a first similar image sub-model and a second similar image sub-model respectively according to the first similar image sub-group and the second similar image sub-group. Combining a first similar image sub-model to a first position model, and combining a second similar image sub-model to a second position model. Finally, combining the first position model and the second position model to a scene model.

Provided are a scalable data fusion method and related products. The scalable data fusion method is applied in a central device and includes: receiving sensing data transmitted by each of M first edge devices, wherein M is an integer equal to or greater than 1; fusing the sensing data transmitted by each of the M first edge devices to obtain M pieces of fused data respectively corresponding to the M first edge devices; distributing the M pieces of fused data to the M first edge devices respectively; receiving object information transmitted by each of the M first edge devices, wherein the object information is obtained based on the fused data; and integrating the object information transmitted by each of the M first edge devices and construct surrounding information based on the integrated object information.

Methods, devices and storage media for data processing are provided. One of the methods include: obtaining a target image, wherein the target image comprises at least one tubular image; determining a spatial distribution feature and an image feature of each of the at least one tubular image; obtaining, based on a tubular structure recognition model, at least one fusion feature respectively corresponding to the at least one tubular image by fusing the spatial distribution feature and the image feature of each of the at least one tubular image; and recognizing, based on the tubular structure recognition model and the at least one fusion feature respectively corresponding to the at least one tubular image, at least one tubular structure respectively corresponding to the at least one tubular image.

A method includes: capturing one or more images of an unorganized collection of items inside a first machine; determining one or more item types of the unorganized collection of items from the one or more images, comprising: dividing a respective image in the one or more images into a respective plurality of sub-regions; performing feature detection on the respective plurality of sub-regions to obtain a respective plurality of regional feature vectors, wherein a regional feature vector for a sub-region indicates characteristics for a plurality of predefined local item features for the sub-region; generating an integrated feature vector by combining the respective plurality of regional feature vectors; and applying a plurality of binary classifiers to the integrated feature vector; and selecting a machine setting for the first machine based on the determined one or more clothes type in the unorganized collection of items.