7 results about "Aerial photography" patented technology

The invention discloses a variable-focus aerial photography cradle head device. The variable-focus aerial photography cradle head device comprises a cradle head base, wherein a camera is fixed on the middle part of the cradle head base; a cradle head base left panel and a cradle head base right panel which are connected with the two ends of the cradle head base are connected with one end of a cradle head left panel and one end of a cradle head right panel respectively; a cradle head back panel and a cradle head front panel are connected between the other end of the cradle head left panel and the other end of the cradle head right panel; the cradle head back panel is connected with a cradle head outer panel; the cradle head front panel is connected with a cradle head inner panel; an output shaft of a first stepping motor is connected with the cradle head back panel; an output shaft of a second stepping motor is connected with the cradle head base left panel; an output shaft of a third stepping motor is used for driving a focusing lens on the camera to rotate through a belt pulley; two adjustable-position baffle plates arranged on a belt are matched with limiting switches. The variable-focus aerial photography cradle head device has a cross rolling function and a pitching function, can meet the requirement on near-distance framing of a far object by accurately controlling the focusing lens, is easy to realize, is convenient to operate, and is flexible to control.

The invention discloses an aerial image identification based power grid geographical wiring diagram drawing method. The method comprises: selecting an eigenvalue of a substation or a tower, and performing fitting to make a template; intercepting an image frame from an aerial video; performing gray conversion on an image; performing histogram equalization reinforcement; obtaining a binaryzation effect picture; obtaining a denoising effect picture; obtaining a foreground picture only containing edge information; obtaining a graph outline of a suspected substation or tower; matching extracted edge contour information with a feature template of the substation or the tower, and performing marking when the matching is successful; connecting key points of the substation or the tower and performing drawing in a power grid geographical wiring diagram; and manually checking the power grid geographical wiring diagram. The method is high in efficiency, accurate in position and low in error rate, saves manpower and material resources, realizes automatic computer drawing, and greatly improves the efficiency and accuracy of drawing the power grid geographical wiring diagram.

The invention relates to an aerial view semantic segmentation label generation method based on inverse perspective transformation and point cloud projection, and the method comprises the steps: data collection: synchronizing camera and laser radar data at the same moment through a synchronization signal, and enabling the time stamp difference of all camera and laser radar sensor data at each moment not to exceed a set value; data labeling: performing joint labeling on m images and n point cloud data at the same moment, marking a static area of the road surface on the images, and marking a dynamic object 3D bounding box on the point cloud; the method comprises the following steps: generating a road surface region of a BEV label through inverse perspective transformation, perspective-perspective-based on the inverse perspective transformation of affine geometry, perspective-perspective the semantic segmentation label of the road surface at each camera visual angle to a BEV canvas, splicing the semantic segmentation labels, and carrying out refined processing on a spliced picture. According to the method, the accurate aerial view semantic segmentation label is directly generated from the original image and the point cloud which are synchronized at a certain moment, so that the aerial view is prevented from being acquired and labeled in a way of aerial photography of a road surface by an unmanned aerial vehicle, and the cost is reduced.

The invention discloses a night suspicious person supervision system based on community networking. The system comprises the following function modules: a property monitoring system, a power supply module, a display module, a storage module and an infrared ray covering net which is built by utilizing combination of infrared ray induction equipment, so that the infrared ray induction equipment cancover a community jurisdiction area or a hidden area of the community jurisdiction area; wherein the hidden area is an indoor or outdoor area which is not easy to find by people; the infrared coveringnet can automatically sense the heating object and send the coordinates of the heating sensing point to the property monitoring system; the property monitoring system analyzes the position, calls theimage acquisition module to shoot if the position is in the coverage area of the image acquisition module, and dispatches related personnel to carry out on-site exploration if the position is in thenon-coverage area of the image acquisition module; the image acquisition module is used for carrying out stable real-time image acquisition on the monitored area; the system comprises a controllable camera system and an aerial photography device, and the camera and the aerial photography device can be controlled by a property monitoring system. According to the invention, through setting infrareddetection of the hidden area, hiding of lawbreakers at night can be effectively avoided, and community public security is improved.