81 results about "Appearance modeling" patented technology

The invention relates to a vehicle body and a sky train vehicle. The vehicle body comprises two transparent side walls and a transparent bottom wall. The two transparent side walls are oppositely arranged along the width direction of the vehicle body, and the transparent bottom wall is arranged between the bottoms of the two transparent side walls. The vehicle body and the sky train vehicle have the advantages that the technical problems of poor sightseeing effects and the like due to conservative appearance modeling, heavy weights and poor internal transparency of existing sky train vehiclescan be solved by the aid of the vehicle body and the sky train vehicle.

The embodiment of the invention discloses a video target tracking method based on local weighted sparse feature selection, and the method comprises the following steps: carrying out the local appearance modeling of a target, and constructing a local discrimination dictionary for representation; sampling the search area of the current frame, and selecting a target candidate sample by taking the sparse decomposition coefficient of the sample as a feature; adding local noise energy to the reconstruction error through a weighting function, enhancing the representation capability and discriminationstability of the reconstruction error under noise interference, and selecting an optimal tracking result; utilizing an updating method combining long time and short time, using a self-adaptive noiseenergy threshold value as a condition for executing updating, and selecting two local dictionaries randomly for updating. According to the embodiment of the invention, the performance of sparse feature selection is improved through the methods of local discrimination dictionary learning, noise energy analysis and weighted decision, the purpose of improving the tracking accuracy is achieved, the interference of background noise information on target detection is suppressed, and the stability of model discrimination is improved.

The invention discloses a modeling method suitable for the appearance of a single aviation conduit. The modeling method comprises the following steps of acquiring the three-dimensional depth data of the single aviation conduit from any fixed visual angle by utilizing a depth camera; processing the acquired three-dimensional depth data, for example, converting the three-dimensional depth data intothe point cloud data, denoising and sampling the point cloud data, and calculating the normal vector of each point cloud; extracting the central axis of the aviation conduit by adopting a cylinder subdivision method; fitting each segmented cylindrical surface of the aviation conduit by using a cylindrical fitting algorithm, and extracting the radius of each segmented cylindrical surface; and constructing a three-dimensional digital model of the whole aviation conduit through a three-dimensional modeling software by utilizing the extracted central axis and the radius of each segmented cylindrical surface. According to the method, the problem that in the prior art, the single aviation conduit appearance modeling is difficult to accurately and rapidly achieve is solved, the aviation conduit modeling efficiency is improved, and the high-quality, stable and high-efficiency modeling method for the single aviation conduit parts is achieved.

An approach for re-identifying an object in a first test image is presented. Brightness transfer functions (BTFs) between respective pairs of training images are determined. Respective similarity measures are determined between the first test image and each of the training images captured by the first camera (first training images). A weighted brightness transfer function (WBTF) is determined by combining the BTFs weighted by weights of the first training images. The weights are based on the similarity measures. The first test image is transformed by the WBTF to better match one of the training images captured by the second camera. Another test image, captured by the second camera, is identified because it is closer in appearance to the transformed test image than other test images captured by the second camera. An object in the identified test image is a re-identification of the object in the first test image.

The invention relates to a connecting structure of motorcycle covering pieces and a front body covering piece assembly provided with the connecting structure. The adjacent edges of two covering pieces are overlapped, one of the covering pieces is bended and extended outwards to have an overlapping sheet at the edge of an overlap edge, the plane deviated from the outer surface of the covering piece on the overlapping sheet is provided with a hollow lug boss of which the longitudinal section is n-shaped, and the top surface of the lug boss is provided with a center hole; and the inner lateral surface of the edge adjacent to the other covering piece is provided with a cylinder corresponding to the center hole of the lug boss, the cylinder is inserted into an inner hole of the lug boss from the downside of the lug boss, and the lug boss is connected with the cylinder through a tapping screw screwed in from the top surface of the lug boss. The connecting structure makes the connections between the motorcycle covering pieces be firm and reliable and have no coupling screws exposed on the outer surfaces of the covering pieces so that the outer surfaces of the covering pieces are more beautiful and smooth; and the front body covering piece assembly of a motorcycle consists of a plurality of covering pieces through connection to have easy appearance modeling, the joints have no exposed screws, and the outer surfaces have natural and beautiful transition.

The invention provides a fishing reel capable of assembling and disassembling a rocker arm assembly through one hand. The fishing reel capable of assembling and disassembling the rocker arm assembly through one hand comprises a fishing reel body, a body cover, a winding reel, a transmission device and a rotator, the transmission device comprises a gear plate and the rocker arm assembly, the rocker arm assembly is connected with a center axis hole of the gear plate in an inserted mode, the rocker arm assembly comprises a hexagon heart, a rocker arm sleeve, a rocker arm and a handle, the rocker arm hexagon heart is connected with the rocker arm sleeve in an inserted mode, the rocker arm sleeve is connected with one end of the rocker arm, and the other end of the rocker arm is movably connected with the handle; the rocker arm assembly further comprises a control rod, two or more stop blocks, a ring spring and a tension knob, the control rod is inserted into a hexagon heart through hole of the rocker arm hexagon heart, and the stop blocks and the ring spring are assembled on the rocker arm hexagon heart. According to the fishing reel which is capable of conducting flexible combination and assembling and disassembling the rocker arm assembly through one hand, parts are simple, appearance modeling is easy, products are diversified, and the cost of an enterprise is greatly reduced.

Personal object based archival systems and methods are provided for processing and compressing video. By analyzing features unique to a user, such as face, family, and pet attributes associated with the user, an invariant model can be determined to create object model adapters personal to each user. These personalized video object models can be created using geometric and appearance modeling techniques, and they can be stored in an object model library. The object models can be reused for processing other video streams. The object models can be shared in a peer-to-peer network among many users, or the object models can be stored in an object model library on a server. When the compressed (encoded) video is reconstructed, the video object models can be accessed and used to produce quality video with nearly lossless compression.

The invention provides a self-service moxa-moxibustion and massage timing health care kiosk. The self-service moxa-moxibustion and massage timing health care kiosk is a comprehensive health care service device / product which is fashionable in appearance molding, low in space occupation and capable of being flexibly moved, and the self-service moxa-moxibustion and massage timing health care kiosk ismainly arranged in a public community or a large market or an office building or a science park or a business center, provides self-service moxa-moxibustion and massage timing health care services for people, and meets the requirements of people for body health care anytime and anywhere according to the needs. The self-service moxa-moxibustion and massage timing health care kiosk belongs to a technologically innovative product in the field of share timing services, reservation service can be conducted through a mobile phone APP system and a membership service system, and people can enter thekiosk for timing service at any time. While the kiosk provides the timing health care service, advertising revenues can be obtained by playing related product promotional videos or other advertising short films through a display system outside the kiosk and audio and video equipment inside the kiosk by turns, and commodity sales revenues are obtained through food and drink vending machines in thekiosk. The self-service moxa-moxibustion and massage timing health care kiosk as a comprehensive and integrated business service device / product can conduct direct sales and channel agent sales in a device / product form; the self-service moxa-moxibustion and massage timing health care kiosk as an innovative startup project can provide direct management, authorized operation, cooperative management,franchising and service agent for the market, and the kiosk has good economic benefits and development prospects.