Abstract: Autonomous vehicles utilize perception and understanding of road users and road objects to predict behaviors of the road users and road objects, and to plan a trajectory for the vehicle. Improved perception and understanding of the AV's surroundings can improve the AV's behavior around drivable objects, non-drivable road objects, construction zones, and temporary road closures. Improved perception and understanding of the AV's surroundings can also reduce the chances of the AV getting stuck and the need to be retrieved physically. To offer additional understanding capabilities, an additional understanding model is added to the perception and understanding pipeline to improve classification of road objects and extraction of attributes of the road objects. The implementation of the understanding model itself and placement of the model within the pipeline balance recall and precision performance metrics and computational complexity.

Abstract: Autonomous vehicles utilize perception and understanding of vehicles to predict behaviors of the vehicles, and to plan a trajectory. Understanding of attributes of vehicles may be improved through sensor fusion. Sensor fusion can be computationally expensive and may be difficult to implement in a real-time vehicle understanding system. To limit computational complexity while benefiting from machine learning across modalities, sensor fusion may be selectively implemented for a subset of task groups of a multi-task machine learning model. In some cases, part-based understanding may be implemented before fusion to limit the features being fused together to part features that are most salient for the task group. In addition, sensor data and features that may be fused together can be limited to sensor data and features within a desired field of view. A model that implements sensor fusion may be disabled for objects that are beyond a threshold distance.

Abstract: A method, a device and a security system for image data processing based on VR or AR are disclosed. In one aspect, an example image data processing method includes reconstructing, based on three-dimensional (3D) scanned data of a containing apparatus in which objects are contained, a 3D image of the containing apparatus and the objects contained in the containing apparatus. The reconstructed 3D image is stereoscopically displayed. Manipulation information is determined for at least one of the objects in the containing apparatus based on positioning information and action information of a user. At least a 3D image of the at least one object is reconstructed based on the determined manipulation information. The at least one reconstructed object is presented on the displayed 3D image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data representing a sensor measurement of a scene captured by one or more sensors to generate an object detection output that identifies locations of one or more objects in the scene. When deployed within an on-board system of a vehicle, the object detection output that is generated can be used to make autonomous driving decisions for the vehicle with enhanced accuracy.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data representing a sensor measurement of a scene captured by one or more sensors to generate an object detection output that identifies locations of one or more objects in the scene. When deployed within an on-board system of a vehicle, the object detection output that is generated can be used to make autonomous driving decisions for the vehicle with enhanced accuracy.

Abstract: The present disclosure relates to a method, a device and a system for inspecting a moving object based on cosmic rays, pertaining to the field of radiation imaging and safety inspection techniques. The method includes: detecting whether a speed of the inspected moving object is within a preset range; recording a motion trajectory of the moving object with a monitoring device; acquiring information about charged particles in the cosmic rays with a position sensitive detector, the information about charged particles including track information of the charged particles; determining the moving object by matching positions of the motion trajectory and the track information; reconstructing the track of the charged particles according to the information about the charged particles; and recognizing the material inside the moving object based on the track reconstruction.

Abstract: A method, a device and a security system for image data processing based on VR or AR are disclosed. In one aspect, an example image data processing method includes reconstructing, based on three-dimensional (3D) scanned data of a containing apparatus in which objects are contained, a 3D image of the containing apparatus and the objects contained in the containing apparatus. The reconstructed 3D image is stereoscopically displayed. Manipulation information is determined for at least one of the objects in the containing apparatus based on positioning information and action information of a user. At least a 3D image of the at least one object is reconstructed based on the determined manipulation information. The at least one reconstructed object is presented on the displayed 3D image.

Abstract: Inspection devices and inspection methods are disclosed. The inspection method includes: performing X-ray scanning on an object being inspected so as to generate an image of the object being inspected; dividing the image of the object being inspected to determine at least one region of interest; detecting interaction between a cosmic ray and the region of interest to obtain a detection value; calculating a scattering characteristic value and/or an absorption characteristic value of the cosmic ray in the region of interest based on size information of the region of interest and the detection value; and discriminating a material attribute of the region of interest by means of the scattering characteristic value and/or the absorption characteristic value. With the above technical solutions, inspection accuracy and inspection efficiency may be improved.

Abstract: The present disclosure relates to a method, a device and a system for inspecting a moving object based on cosmic rays, pertaining to the field of radiation imaging and safety inspection techniques. The method includes: detecting whether a speed of the inspected moving object is within a preset range; recording a motion trajectory of the moving object with a monitoring device; acquiring information about charged particles in the cosmic rays with a position sensitive detector, the information about charged particles including track information of the charged particles; determining the moving object by matching positions of the motion trajectory and the track information; reconstructing the track of the charged particles according to the information about the charged particles; and recognizing the material inside the moving object based on the track reconstruction.

Abstract: Smoking device (10) comprising a first device (20) and a second device (30). The first device (20) comprises an accumulator for storing electric energy and releasing it to a heating device (22) as a response to a sensor device (24) detecting a suck/draw of the smoking device (10) by a consumer. It further comprises a first air inlet (25) through which an airflow enters said first device (20), passes said heating device (22) and streams out through a first air outlet (26). The second device (30) comprises an agent (33), a second air inlet (35) through which air enters said second device (30), passes through said second device (30), releases said agent (33) by means of dispensing means (37) and streams out through said second air outlet (36) into the mouth of a consumer. Charging means (40) for use with a smoking device (10) and method for using said smoking device (10).

Abstract: A very high power fiber light source can be realized by using a high concentration of doping and by pumping the cladding of the doped fiber. The light that enters the cladding will then enter the core and amplified spontaneous emission will result. With this arrangement, higher power, a broader emission spectrum, and low radiation sensitivity can be achieved. These devices can also be configured as amplifiers.

Abstract: The RIN (random intensity noise) component of the random walk error of a fiber optic gyroscope can be reduced by utilizing an unpolarized light signal during processing. By depolarizing the light wave modulated by the fiber optic sensing coil or combining it with the unmodulated light wave of orthogonal polarization, a 3 db reduction in RIN can be achieved.