10 results about "Imaging - action" patented technology

Disclosed are methods of imaging a vehicle using an unmanned aerial vehicle (UAV) according to a predetermined imaging plan. The UAV comprises one or more sensors. The imaging plan comprises one or more imaging actions. A first method comprises detecting a characteristic of the vehicle using the one or more sensors, and calculating a flight waypoint corresponding to each imaging action based on the detected characteristic and the imaging action. A second method comprises detecting positions of target features of the vehicle using the one or more sensors, and carrying out the imaging actions based on the detected positions. Also disclosed are systems and computer programs for carrying out the methods.

Provided is an endoscope system, control method, and control program that can suppress a decrease in the quality of a moving image display and perform imaging based on special light. A light source device (5) repeatedly performs the following actions: continuously irradiating illumination light of a first characteristic over a first period that spans a plurality of consecutive imaging action frames, and then irradiating illumination light of a second characteristic over a second period that spans at least one imaging action frame. A display (7) displays a moving image using an imaging image obtained from an imaging element (23), displays the moving image in accordance with the imaging image for the first period for the first period, and displays the moving image in accordance with the imaging image for a period different from the second period for the second period.

The invention is suitable for the technical field of nuclear power, and provides a control method of an irradiation nuclear fuel rod underwater inspection device, a controller and electronic equipment.The method comprises the steps that when fuel lifting equipment is located at an initial inspection position, all shooting equipment is controlled to execute shooting actions so as to obtain an annular image of one end of an irradiation nuclear fuel rod; and in the process that the fuel lifting equipment runs towards the other end of the irradiation nuclear fuel rod, a second distance measured by the distance measuring instrument is obtained, and all the shooting equipment is controlled to execute the shooting action until the difference between the second distance and the first distance is equal to the length of the irradiation nuclear fuel rod. And obtaining an annular image of the irradiated nuclear fuel rod from one end to the other end. Through the method, the shooting time can be greatly shortened.

The invention discloses an expression package automatic generation and management method, which comprises the following steps that: after a user inputs a semantic text, a system firstly analyzes and extracts key semantic elements, and then retrieves visual common knowledge elements strongly associated with the key semantic elements in an expression package structured knowledge base; and the two are assembled by fusion logic to generate a quintuple structured description (including individual relationship, image action, expression, blank space and dialogue content) of a complete definition picture. And after the description is coded into a condition vector, a condition generation model is driven to synthesize a target expression package image. If the user adopts, the result and the quintuple description thereof are fed back to the knowledge base to continuously optimize the system. According to the method, a'quintuple 'intermediate layer is introduced, and the fuzzy intention is converted into an accurate structured script, so that the generation result is highly controllable in style, action, composition and blank space and meets the expectation, and the one-time generation success rate is greatly improved.

A sample analysis system (10) includes a sample storage device (100), a sample measuring device (200), a sample container transfer device (300), a first imaging device (400), and a control device (500). The control device (500) is configured to: obtain a first target image based on an image captured by the first imaging device (400) performing a first imaging action, and output at least one of the following: the first target image, a determination result indicating whether there is coagulation in the intermediate liquid layer (32), and a determination result indicating the degree of coagulation in the blood sample (30); the first target image includes at least an image showing the interface liquid surface (321) or interface liquid layer in a two-dimensional and / or three-dimensional form, which can be used as a basis for determining whether there is coagulation in the intermediate liquid layer (32) and / or as a basis for determining the degree of coagulation in the blood sample (30). This reduces the probability of missed detection of premature coagulation in the blood sample (30) and improves the accuracy of determining whether a coagulation occurs in the blood sample (30) before sampling.

The application provides a high-resolution agile optical and laser integrated satellite imaging method, which comprises the following steps: step one, acquiring the central point longitude and latitude of a satellite imaging plan target, an imaging orbit height, an imaging time length and scene parameters; step two, combining a satellite maneuvering capability to perform a symmetrical M satellite pointing imaging action sequence deduction with the central point of the target as the center to obtain an attitude maneuvering angle of each time; step three, according to the scene parameters T and the attitude maneuvering angle, sequentially judging the availability of laser data under M satellite imaging tasks; step four, marking different virtual channel marks on different types of working mode marks, laser data and engineering measurement data; and step five, recording and transmitting the optical, laser and auxiliary data according to the set working mode and signal path.

Disclosed are methods of imaging a vehicle using an unmanned aerial vehicle according to a predetermined imaging plan. The UAV comprises one or more sensors. The imaging plan comprises one or more imaging actions. A first method comprises detecting a characteristic of the vehicle using the one or more sensors, and calculating a flight waypoint corresponding to each imaging action based on the detected characteristic and the imaging action. A second method comprises detecting positions of target features of the vehicle using the one or more sensors, and carrying out the imaging actions based on the detected positions

The invention, which relates to the technical field of image recognition, discloses an AI-image-motion-recognition-based railway operation practice examination system comprising an AI motion recognition module, a motion matching module, a skill analysis module, a skill modeling module, and an examination decision module. According to the method, operation action time sorting adjustment is carried out through action time consumption, an operation action initial assessment score is generated, the time information of a target person during gesture feature sequence collection is obtained, the action performance of an operator is deeply analyzed from the time dimension, and an action recognition response assessment coefficient is obtained based on time response comprehensive assessment; according to the method, skill levels are layered, skill dimensions and action complexity of different levels are set, a three-dimensional skill assessment model is constructed, an operation action initial assessment score, an action recognition response assessment coefficient and a quantitative assessment index of each skill dimension are combined, and operation action assessment efficiency analysis is performed. And a reliable basis is provided for intelligent grading judgment of practical examination of target personnel.

The invention relates to a dynamic blurred image motion recognition method and system for fitness training. The method comprises the following steps: acquiring multi-angle video stream data of a fitness area and an affiliated water area, and performing reflection removal and water wave dynamic suppression preprocessing to obtain an adaptive video stream; inputting a posture recognition model to obtain a human body posture key point and multi-target tracking data, analyzing an instrument state change sequence to obtain an interaction state detection threshold, and combining the two to input an action anomaly classification model to output an anomaly type label; and extracting corresponding risk data, calculating abnormal static and coma event probabilities, and integrating multi-source data to generate a comprehensive risk assessment report containing risk types, probabilities, influence ranges and disposal suggestions. By adopting the method, the defects of manual supervision can be overcome, the multi-scene requirements of fitness area instrument safety and auxiliary water area drowning protection are met, and the intelligence and comprehensiveness of fitness place safety protection are improved.

An imaging element includes: a photodiode, a first FD, a second FD, a TRG transistor, an amplification transistor, a DGC transistor for switching a conversion gain, when converting charges into a pixel signal, to a high gain or a low gain, a capacitor, an OFG transistor for transferring charges overflowing from the photodiode to the second FD, and an RST transistor. During an imaging action involving a long exposure time, after reset is carried out, with the conversion gain being switched to the high gain, the pixel signal is read and employed as a high-gain reset signal. Then, after the TRG transistor is conducted, the pixel signal is read and employed as a high-gain signal. A first signal which is a difference between the high-gain signal and the high-gain reset signal is outputted.