41 results about "Right eyeball" patented technology

The invention relates to a human face image recognizing method based on the geometric size normalization of a human face, belonging to image processing technical field, and comprising the steps of: determining the coordinates of the left and right eyeballs on an input human face image, and according to the coordinates, rotating the image to the horizontal position to obtain a new human face image 2, then determining the coordinates of left and right eyeballs and mandible of the new human face image 2, specifying the numeric value of normalized geometric size of a human face, zooming in or out the new human face 2 to obtain another human face image 3 meeting the standard distance; according to the coordinates of left and right eyeballs and mandible of the human face image 3, cutting the human face image 3 to obtaina standard normalized human face image; forming training-set, known and to-be- recognized human face images into human face images of normalized geometric size and extracting human face characteristics, and in a known human face database, adopting the methods of calculating similarity and sequencing according to the similarity to recognize the human face. The invention obviously improves the visual effect of a human face and makes a higher increase in the recognizing ratio.

The invention discloses a video face feature point location method, which is applied to the technical field of image processing. The method mainly comprises the steps that firstly, feature point location is carried out on the first frame of a video to acquire the initial position information of left and right eyeballs, two mouth points and the center of upper and lower lips, which facilitates tracking the points in subsequent video frames; secondly, a large displacement optical flow technology is used for each frame of a follow-up video to establish the variable optical flow field of an imageto track the positions of six points initialized in the first part in the current frame; and thirdly, the tracked position information of six points in the second part is used for feature point location. According to the invention, accurate feature point location can be carried out for rich expressions.

The invention discloses a virtual reality device and a control method and apparatus for a display screen of the same. The virtual reality device comprises a first eyeball tracking module, a second eyeball tracking module, a processor and a display screen, wherein the first eyeball tracking module is set to acquire a left eyeball state of a user; the second eyeball tracking module is set to acquire a right eyeball state of the user; and the processor is set to control an on/off state of the display screen according to the left eyeball state and the right eyeball state. The left eyeball state and the right eyeball state of the user are tracked, and the on/off state of the display screen is controlled according to the left eyeball state and the right eyeball state of the user, so that the display screen is controlled to be turned off when the user closes the eyes, the power consumption of the virtual reality device can be effectively reduced, and the hardware cost is not increased.

The invention discloses a spatial RSSR mechanism based biomimetic eye movement mechanism. The mechanism comprises a bottom plate, a left eyeball movement mechanism, a right eyeball movement mechanism and two eyelid movement mechanisms; each eyeball movement mechanism comprises a steering gear, a connecting rod, a bearing, a transmission shaft, a pin, a supporting frame, a circular ring, an eyeball and a camera; each eyelid movement mechanism comprises another steering gear, another connecting rod, an upper eyelid and a lower eyelid; the steering gears and the supporting frames are fixed on the bottom plate through screws; the connecting rods are respectively connected with the steering gears, the transmission shafts, the circular rings, the upper eyelids and the lower eyelids through the screws; the transmission shafts are connected with the supporting frames through pins and fixed on the circular rings through two bearings; the cameras are connected with the circular rings through the screws; the eyeballs sleeve the circular rings; the steering gears drive the connecting rods to enable the eyeballs to rotate up and down about the transmission shafts as well as rotating leftwards and rightwards about the pins, so as to open and close the upper and lower eyelids. The mechanism is compact in structure, small in space used, and flexible, accurate and reliable to move; the left and right eyeballs are independent from each other; the two eyeballs can move in the same direction or different directions.

The embodiment of the invention provides an image displaying method and device, and virtual-reality equipment. The method is applied to the virtual-reality equipment, and comprises the following steps: acquiring a left eye panoramic image and a right eye panoramic image, and importing the left eye panoramic image into a preset left eyeball model to obtain a left eye panoramic environment image; importing the right eye panoramic image into a preset right eyeball model to obtain a right eye panoramic environment image; respectively determining the data to be watched by the left eye and the righteye of a user from the left eye panoramic environment image and the right eye panoramic image; rendering to obtain the left eye image and the right eye image by using the determined data to be watched by the left eye and the right eye of the user; and synchronously displaying the left eye image and the right eye image. Through application of the technical scheme provided by the embodiment of theinvention, the user immersion is improved when the image displaying is performed.

The invention discloses a bevel gear differential-motion human eye movement imitating mechanism. The bevel gear differential-motion human eye movement imitating mechanism comprises a left eyeball movement mechanism, a right eyeball movement mechanism and an eyelid movement mechanism. As for each eyeball movement mechanism, two central bevel gear, a bevel planet gear and a tie rod constitute a differential gear train, each bevel planet gear is in rigid connection with each eyeball, independent rotation of the two central bevel gears is achieved through motors, the independent rotation is combined into rotation of two degrees of freedom of the bevel planet gears, and therefore the eyeballs can rotate with the two degrees of freedom in the vertical direction and the horizontal direction. Two eyelids are in rigid connection with each other through a rotary shaft and a synchronous belt wheel, the other belt wheel is in rigid connection with one motor, the two belt wheels are in transmission with each other through a synchronous belt, and opening and closing of the eyelids can be achieved through rotation of the motors. The bevel gear differential-motion human eye movement imitating mechanism is compact in structure, small in occupied space, and flexible, accurate and reliable in movement, the left eyeball and the right eyeball are independent from each other, and the two eyeballs can move in the same direction and in the different directions.

The invention discloses an anthropomorphic expression robot based on an electroactive polymer driver. The anthropomorphic expression robot based on the electroactive polymer driver comprises a head-shaped robot consisting of a skull cover and upper jaw part, an eyebrow part, an eyelid part, an eyeball part and a lower jaw and mouth part, wherein independent eyebrow driving assemblies are arrangedon a left eyebrow and a right eyebrow of the eyebrow part, the eyebrow driving assemblies drive the left eyebrow and the right eyebrow to move up and down and/or rotate left and right, independent eyelid driving assemblies which drive a left eyelid or a right eyelid to open and close up and down are arranged on the left eyelid and the right eyelid of the eyelid part correspondingly, independent eyeball driving assemblies which drive a left eyeball or a right eyeball to rotate are arranged on the left eyeball and the right eyeball of the eyeball part correspondingly, the lower jaw and mouth part comprises a lower jaw, a mouth and a lower jaw driving assembly, and the lower jaw driving assembly drives the lower jaw to open and close to drive the mouth to open and close. According to the anthropomorphic expression robot based on the electroactive polymer driver, the motion range of each part is the same as the motion range of the corresponding part of human, various basic expressions of the human can be flexibly simulated, and the anthropomorphic expression robot based on the electroactive polymer driver has the advantages of light and compact structure, no noise, low energy consumption and the like.

The invention provides a bio-robot eye driving mechanism. The bio-robot eye drying mechanism comprises an upper eyelid, a lower eyelid, a stand, a left eyeball, a right eyeball, a steering engine, a swing rod, a connection rod, a pull rod and a ball connection rod.

The invention relates to a tree shrew retina ischemic injury experiment model adopting photochemical induction, and belongs to the technical field of clinical medicine, pharmacy and cell biology. The experiment model is obtained through steps as follows: a healthy adult tree shrew is selected and is anaesthetized by 40 mg*kg(-1) of 2.5% sodium thiopental through intraperitoneal injection; the tree shrew is fixed on an operating table, and 2.75% rose Bengal normal saline is injected from the sublingual vein of the animal in a dose of 0.031 ml/10 g; 2 drips or 3 drips of a 0.25% compound tropicamide solution are utilized to dilate pupils; after rose Bengal is circulated for 10 min, a small animal cerebral thrombosis experimental device with the patent number of ZL201420068737.2 is adopted to irradiate a left eyeball or a right eyeball, so that vascular endothelial injury and platelet aggregation induce thrombogenesis, and the surface temperature of the irradiated part is controlled to be 37.0 DEG C plus or minus 0.1 DEG C; the thermal insulation is performed, the animal is placed back to a cage after coming round, fundus retina photographing is performed after the experiment is finished for 4 h, 24 h and 72 h; fundus artery thrombogenesis and retina injury change are dynamically observed with a conventional method. The model has the advantages of simplicity and convenience in operation, good repeatability and low experiment cost.

The invention is applicable to the technical field of video induction, and provides a myopia prevention method based on a video induction technology. The method comprises the following steps of: shooting a main image in real time, and identifying and acquiring a face image in the main image; recognizing and calculating position coordinates of left and right eyeballs in the face image, and calculating fixation angles of the left and right eyeballs through the position coordinates; calculating camera shooting distances from the left eyeball and the right eyeball to a camera shooting unit, and respectively calculating eye use distances from the left eyeball and the right eyeball to a fixation point according to the camera shooting distances and the fixation angle; and analyzing whether the eye use distances and the stay time of the eye use distances exceed corresponding preset prevention thresholds or not, and if so, generating feedback reminding information to remind a user. The invention further provides a myopia prevention system based on the video induction technology. Therefore, the actual eye use distance between the eyes of the user and the gazed point can be updated in real time, the reading posture of the user can be reminded and corrected in time, and then the effect of preventing myopia is achieved.

The invention provides a fundus blood vessel image segmentation method based on self-supervised learning. The method comprises the following steps of S1, setting a data set which comprises a labeled image sample D and label-free left and right eyeball image information XT belonging to (L, R) of a same patient; S2, constructing a self-supervised network which is composed of two identical U-Net networks based on an auxiliary task, wherein the two parallel U-Net networks are respectively marked as a baseline (a) and a baseline (b); S3, constructing an image segmentation loss model, respectively inputting the labeled image sample D and the label-free left and right eyeball image information XT belonging to (L, R) of the same patient into the baseline (a) and the self-supervision module composed of the baseline (a) and the baseline (b), optimizing the parameters of a baseline (a) network through a cross entropy loss function and a local consistency comparison loss function, wherein the network parameters of the baseline (b) in the training process are obtained through the momentum transmission of the baseline (a); and S4, inputting the to-be-detected left and right eye image information to any network in the optimized self-supervised network for image segmentation processing to obtain a final segmentation result. Through the above method, the accurate segmentation can be performed on the fundus blood vessel image.

The invention discloses a face rigid body model, a fixation point detection method and device and a storage medium, and the method comprises the steps: obtaining a first visible light face image of a current user, which is forwardly shot by an image sensor, and obtaining a preset number of feature points of the face of the current user from the first visible light face image; determining a left eyeball center three-dimensional coordinate, a right eyeball center three-dimensional coordinate and a face center three-dimensional coordinate of the current user based on the preset number of feature points; and respectively establishing a left eye vector and a right eye vector from the left eyeball center three-dimensional coordinate and the right eyeball center three-dimensional coordinate to the face center three-dimensional coordinate, and mapping the left eye vector and the right eye vector to the face three-dimensional model to obtain a face rigid body model of the current user.

The invention discloses a robot and interaction method thereof. The robot comprises a head shell, a control device and a sensor perceptual system; a left eyeball, a right eyeball, an eyeball transmission mechanism, a loudspeaker and a carrier frame are arranged inside the head shell; the sensor perceptual system comprises a pyroelectric infrared sensor and a range sensor, the pyroelectric infraredsensor is located inside the left eyeball, and the range sensor is located inside the right eyeball, the left eyeball and the right eyeball are both rotationally connected with the head shell; the eyeball transmission mechanism comprises a steering engine and a transmission rod, a steering engine disc is installed on a rotating shaft of the steering engine, the left eyeball and the right eyeballare connected with the tail end of the transmission rod in a hinged mode, the head end of the transmission rod is hinged to the steering engine disc, and the steering engine and the loudspeaker are both fixedly connected with the carrier frame; and the pyroelectric infrared sensor, the range sensor, the steering engine and the loudspeaker are all electrically connected with the control device. Therobot has a good active interaction function.

The invention discloses a vestibular ocular reflex recording method for autism spectrum disorder children. The vestibular ocular reflex recording method is characterized in that a first 980nm laser sensor and a second 980nm laser sensor are arranged at the left front part and the right front part of the left side and the right side of a glasses support respectively; a laser beam emitted by the second 980nm laser sensor is incident to the left eye through a beam expanding lens, and a 10-degree angle is formed between the light and an eyeball; a laser beam emitted by the first 980nm laser sensor enters the right eye through the beam expanding lens, and an angle of 10 degrees is formed between the light and an eyeball; and the first 980nm laser sensor is used for measuring the vestibular ocular movement of the right eyeball. Vestibular ocular movement amplitude, frequency and phase of eyeballs are determined through a function relation between eyeball displacement components in the light propagation direction and eyeball displacement, so that vestibular ocular reflex of the autism spectrum disorder children is rapidly recorded. According to the method, the vestibular ocular reflex of the autism spectrum disorder children can be rapidly recorded through a set of glasses type laser sensors, and the vestibular ocular reflex detection efficiency and accuracy of the autism spectrum disorder children are improved.

Validity of a line-of-sight direction detected by a gaze point detection unit is determined by using a positional difference that is a calibration value used for detecting a position of a corneal curvature center. Therefore, it is possible to easily and effectively determine the validity of the line-of-sight direction without additionally using a system or the like for detecting the validity of the line-of-sight direction. Consequently, it is possible to accurately detect line-of-sight directions of various subjects, such as a subject whose left and right eyeballs have different corneal curvature radii or a subject whose line-of-sight directions of left and right eyeballs are largely different due to the influence of strabismus or the like.