9 results about "Wrist Region" patented technology

The invention relates to a method, device and equipment for detecting shopping settlement fraud risk behaviors and a medium, and the method comprises the steps: obtaining a plurality of continuous video frames, and detecting a human body bounding box and a posture key point of a character object in the video frames, thereby obtaining a posture detection result; determining an upper body bounding box according to the human body bounding box, and tracking the upper body bounding box in a plurality of continuous video frames to obtain a motion track; according to the posture detection result and the motion track, determining whether the character object triggers a shopping behavior through track analysis and posture analysis, and if the character object triggers the shopping behavior, outputting and storing a detection record for a shopping behavior triggering event of the character object to obtain a shopping behavior detection result; and under the condition that the shopping behavior detection result represents that a shopping behavior trigger event exists, determining a wrist area image according to the wrist key point, performing commodity identification on the wrist area image through open set target detection, outputting and storing a commodity identification event record, and obtaining a shopping settlement detection result.

The utility model relates to a pressure sensor, a robot and an executive component applied to the robot, the executive component comprises a base body, the shape of the projection of the base body along the thickness direction is the same as that of a hand, the base body is provided with a palm area, a finger area and a wrist area, and the pressure sensor comprises a sensing unit. The sensitive module comprises a plurality of sensitive modules arranged in the palm area and the finger area; each sensitive module comprises a plurality of sensitive assemblies, and each sensitive assembly comprises a substrate, a lower electrode, a composite sensitive layer, an upper electrode and a packaging layer which are sequentially arranged in the thickness direction; the composite sensitive layer comprises a corrugated layer and a film layer, and the corrugated layer and the film layer are attached to each other to form a corrugated structure; the lead unit comprises an upper electrode lead, a lower electrode lead, a common lead and a total output end. The capacitive flexible tactile sensor can solve the problems that an existing capacitive flexible tactile sensor is low in force perception precision, and sensitivity and linearity are reduced along with increase of pressure.

The invention discloses a wrist vein verification method with a lightweight attention mechanism deep learning model. The wrist vein verification method comprises the following steps: acquiring a wrist vein visible light image through an image acquisition device; performing a wrist region-of-interest detection program on the wrist vein visible light image through an image processing device, extracting a wrist region-of-interest image, and performing a blood vessel image enhancement program on the wrist region-of-interest image to obtain a model input image; executing the lightweight attention mechanism deep learning model through an image processing device, and inputting the model input image to extract a feature vector; and comparing the feature vector with the registered wrist feature vector of the person to be tested through the image processing device, if the comparison result is consistent, determining that the verification is successful, and if the comparison result is not consistent, determining that the verification is failed.

A glove having a wrist region, a palm region that extends outwardly from the wrist region and defines a palm plane, at least one digit region extending outwardly from the palm region and terminating at a terminal end, and a surface treatment provided on the palm region or the at least one digit region. The at least one digit region includes a longitudinal axis that extends between the terminal end and the palm region and is parallel to the palm plane. The surface treatment also includes a set of projections that extends outwardly from the palm region or the at least one digit region. Each projection of the set of projections also extends outwardly along an axis that is non-parallel to the palm plane of the palm region or extends outwardly along an axis that is non-parallel to the longitudinal axis of the at least one digit region.

The invention relates to a sports glove, in particular a goalkeeper glove, comprising a backhand part (1), finger areas (11), a thumb area (13) and a wrist area (12), and in which at least one reinforcing element made of expanded thermoplastic elastomer is formed between two layers, extending in the back area. It further relates to the method for manufacturing the backhand part (1) of the sports glove and the use of the sports glove.

An ambidextrous or hand-specific glove including a wrist region, a palm region, and a digit region. The glove is fabricated of nitrile which is resistant to toxic or corrosive substances. These substances include drugs mixed with opioids such as fentanyl and carfentanil. The fingertip regions on the glove may be of a reduced circumference so as to pull the glove material therein tightly around the tips of a user's fingers and thumb. The reduced circumferences fingertip regions helps the user to detect even a faint pulse in a patient. The glove includes a first color exterior surface and a second color interior surface. The first and second colors contrast with one another and this feature serves as a tear indicator to the user.

The application relates to the technical field of logistics automation, and discloses a through method for singular point areas of a shoulder and a wrist of a spherical-wrist 6R industrial robot, which comprises the following steps: firstly, off-line loading of geometric parameters of the robot and presetting of three types of singular judgment thresholds; continuously collecting and buffering joint angles in a servo cycle; solving end poses by means of homogeneous transformation and synchronously calculating a Jacobian matrix; and parallelly completing three types of singular state detection of the shoulder, the elbow and the wrist. The scheme distinguishes two types of operation branches, i.e. singular and non-singular, closes damping in the non-singular state, adopts a standard Jacobian pseudo-inverse to output a motion instruction, starts adaptive damping correction only when the robot approaches a singular boundary, and solves joint speeds by adapting three types of mainstream control modes. The scheme can completely identify all singular configurations of the robot, avoids singular missed judgment to cause equipment out of control, continuously and real-timely identifies dangerous areas, and avoids the problem of large rotation of multiple axes caused by small end displacement.

A glove including a wrist region; a palm region extending outwardly from the wrist region; a plurality of digit regions extending outwardly from the palm region, wherein each digit region of the plurality of digit regions has a longitudinal axis extending along the digit region from the tip of the digit region to the palm region; an interior cavity bounded and defined by the wrist region, the palm region, and the plurality of digit regions, wherein the interior cavity is accessible via an opening defined by the wrist region. A crotch area is provided between adjacent digit regions. At least one gripping zone is provided on at least one digit region. The gripping zone is oriented substantially parallel to the longitudinal axis of the at least one digit region. An exterior surface of at least one crotch area and at least one gripping zone is textured, particularly by micro-etching.

This application relates to methods, apparatus, equipment, and media for detecting fraudulent shopping checkout behavior. The method includes acquiring multiple consecutive video frames, detecting the human body bounding box and pose key points of a person in the video frames to obtain a pose detection result; determining the upper body bounding box based on the human body bounding box, and tracking the upper body bounding box in multiple consecutive video frames to obtain a motion trajectory; determining whether the person has triggered a shopping behavior based on the pose detection result and motion trajectory through trajectory analysis and pose analysis; if the person has triggered a shopping behavior, outputting and saving a detection record for the shopping behavior trigger event to obtain a shopping behavior detection result; and, if the shopping behavior detection result indicates the existence of a shopping behavior trigger event, determining a wrist region image based on wrist key points, performing product recognition on the wrist region image through open set object detection, outputting and saving a product recognition event record to obtain a shopping checkout detection result.