49results about How to "Small model" patented technology

The invention discloses an electric corn medium-term fertilizer distributor which comprises a main frame and an electric motor rack, wherein a fertilizer can is installed on the main frame, the left side and the right side of the lower part of the fertilizer can are respectively provided with a fertilizer apparatus, hoppers and fertilizer pipes are respectively arranged below the discharge ports of the fertilizer apparatuses, and the lower ends of the fertilizer pipes are respectively connected with a furrow opener; the main frame is fixedly connected with the electric motor rack at the front end through pins, a storage battery, an electrical motor and a controller are fixedly installed at the front end of the electric motor rack, and handles are fixedly installed on the side plates at the two ends of the electric motor rack; chain wheels which are installed on a transmission gear are connected with the mounting shafts of the fertilizer apparatuses which are arranged below the fertilizer can through a chain and a clutch, and the two ends of the mounting shafts of the fertilizer apparatuses are respectively provided with a fertilizer amount regulation flange which is connected with the fertilizer apparatuses; and driving wheels and the mounting shafts of the fertilizer apparatuses are driven by the electric motor to operate, and the electric motor is supplied with power by the storage battery. The electric corn medium-term fertilizer distributor is reasonable and reliable in structural design, utilizes the electric motor to provide power, has no pollution, is low in noise, and ensures the fertilizing depth and fertilizing amount of the corn growth medium-term fertilizing.

The invention discloses a ship multi-target tracking method based on a YOLO V5 algorithm, and the method comprises the steps: carrying out the screening and marking of collected ship image data, building a data set, and dividing the data set into a training set, a verification set, and a test set; training the YOLO V5 network by using a training set and a verification set in the self-established data set to obtain a ship detection model based on the YOLO V5 network and a weight file; detecting the test set by using the trained YOLO V5 detection model, outputting a detection result, and evaluating the detection model; based on the trained YOLO V5 detection model, generating a tracking model through DeepSort algorithm processing; and carrying out real-time verification on the generated DeepSort tracking model. According to the invention, marine ship detection and multi-target tracking can be realized, the detection precision is high, the real-time performance is good, and the speed is fast.

The invention discloses a detection algorithm of an animal face key point. The detection algorithm comprises: a network structure is set; the network is divided into two sections, and a first sectionis returned to the bbox to obtain a face frame enabling an animal facial image to be inputted accurately; and the second section is returned to an animal face key point and the animal facial image andan animal facial image intercepted again based on the bbox are inputted, so that context information of the animal face is considered and the key region of the animal face is focused and thus the precise key point detection result is obtained. Besides, a stage-divided training mode is employed during the network training process; at the first stage, augmented samples with the large rotation angleand translation amplitude are used for training; and at the second stage, augmented samples with the small rotation angle and translation amplitude are used for training. The detection algorithm hasthe following advantages: the model is small and the speed is fast; a few of manually calibrated samples are needed; an animal face key point is detected accurately; and the need of real-time beauty makeup for a pet from a user is met.

The invention discloses a multifunctional sugarcane ploughing and sowing all-in-one machinecomprising a machine frame and a driving device; the whole machine structurally comprises a rotary blade shaft assembly, a furrow opener, a water and pesticide spraying device, a fertilizer applying assembly, a seed cutting and arranging assembly, a film spreading device, a soil covering device and a seat bracket in sequence from the first row to the eighth row along the running direction, wherein the film spreading device is attached on the middle lower part of the inner side of a soil dividing and guiding plate of the furrow opener; the water and pesticide spraying device, the fertilizer applying assembly and the seed cutting and arranging assembly are respectively arranged on a platform arranged above the furrow opener; and the soil covering device is attached on the middle upper part of the outer side of the soil dividing and guiding plate at both sides of the furrow opener. The technical problems including incomplete function, complex structure, high cost and poor landform adaptability existing in the traditional similar machine are solved by the technical improvement; the machine has the functions of rotary tilling, furrow opening, water and pesticide spraying, fertilizer applying, seed cutting, film spreading and soil covering, the structure is simplified, the manufacturing cost is reduced, and meanwhile, the production efficiency is increased.

The invention discloses a digital printing machine. The digital printing machine comprises a machine frame, a printing trolley, an operation platform and a conveying mechanism, wherein the printing trolley, the operation platform and the conveying mechanism are arranged on the machine frame; the machine frame comprises a first side plate, a second side plate opposite to the first side plate, a first lower side plate and a second lower side plate opposite to the first lower side plate. A containing space is defined by the first side plate and the second side plate jointly. The operation platform is located on the upper portion of the containing space. The conveying mechanism is used for conveying paper and comprises a paper conveying roller, a transition roller, a first tensioning roller, afirst guide roller, a tension roller, a rubber roller, a first spreading roller, a second tensioning roller, a second guide roller and a paper collection roller. The paper conveying roller, the transition roller, the first tensioning roller, the first guide roller, the tension roller, the rubber roller, the first spreading roller, the second tensioning roller and the second guide roller are contained in the containing space. Thus, the effect that paper is tensioned in the conveying process can be effectively ensured, paper is prevented from winkled, and meanwhile, the overall structure is more compact.

The invention provides a tree branch smashing machine for smashing tree branches. The tree branch smashing machine comprises a material feeding hopper, a shell, a hydraulic system, a material feedingmechanism, a smashing mechanism, a control system, a motor, a material discharging hopper and a rack. According to the tree branch smashing machine for smashing the tree branches, the tree branches are put into a material inlet, a hydraulic cylinder works to drive a material feeding roller to move up and down to compress the tree branches, the control system controls the rotating speed of a hydraulic motor according to displacement information of the hydraulic cylinder detected by a displacement sensor, the hydraulic motor drives the material feeding roller to work to feed the tree branches ofdifferent diameters into a smashing roller, the motor drives the smashing roller to work to smash the tree branches, and the smashed tree branches are discharged out from a material discharging mouthunder the action of gravity. The tree branch smashing machine for smashing the tree branches applies the lever principle and is simple in structure, the control system can control the rotating speedof the hydraulic motor automatically according to the displacement information of the hydraulic cylinder to adapt to the tree branches of the different diameters, occurrence of the blocking situationis effectively prevented, and the tree branch smashing effect and efficiency are improved.

The invention discloses an industrial monitoring video image sharpening method based on a GAN network. The industrial monitoring video image sharpening method comprises the following steps: step 1, acquiring an original industrial video image; 2, preprocessing the image data; 3, detecting whether a trained model is contained or not; 4, building a GAN network; 5, perfomring model training; 6, performing model testing to obtain a corresponding high-definition image; 7, checking the test effect, and if the model can generate a high-definition image according to the test image, determining that the model training is better and can meet the actual application requirements; if the test effect is not good, restarting the step 1 to add training samples, and performing training again; the method has the advantages of simple training process, small model, good effect and high calculation efficiency, and is very suitable for recovery and sharpness processing of the monitoring image in a complex industrial environment.

The invention discloses a book positioning method based on an inventory robot, and the method comprises the following steps: S1, data collection: enabling the robot to obtain an electronic tag of a book through an RFID technology, and transmitting the electronic tag, the coordinates of the robot and the height of an antenna to a processor module; S2, data processing and conversion: extracting bookcodes from the electronic tags, storing the electronic tags, the book codes, robot coordinates and antenna heights in a data storage module, reading data through a processor, converting the data intoan array matrix form, and performing equalization processing on each piece of data; S3, book positioning: inputting the data processed in the S2 into a book positioning module, after the position label is found through the network model, the position label and the book information are transmitted to the data reading module together to achieve book positioning, feature extraction is conducted through the network model, the position of a book can be positioned more accurately and more quickly, the workload of a library administrator is greatly reduced, and the working efficiency is improved.

The invention discloses a direct pressure type jaw crusher. The direct pressure type jaw crusher comprises a fixed jaw body and a movable jaw body, wherein a crushing cavity is formed in the oppositesurfaces of the movable jaw body and the fixed jaw body; the inclination angle of a formed V-shaped clearance is used for stone crushing; a limiting device is arranged between the movable jaw body anda machine body; the back end of the movable jaw body is mounted on an eccentric shaft driven by a power device through a bearing; and under driving of the power device, the eccentric shaft can rotateto drive the movable jaw body to perform reciprocating motion under limiting of the limiting device relative to the fixed jaw body, and at the same time, stone entering the crushing cavity can be extruded for multiple times through change of the V-shaped clearance, and crushed stone is discharged outside the crushing cavity. Through adoption of the direct pressure type jaw crusher, advantages ofcompound pendulum and simple pendulum jaw crushers are maintained, the size is smaller, yield is larger, abrasion is lower, the crusher is more energy-saving, crushing capacity is higher, quality is better, the crusher has the advantages that specification selectivity of a crushed product is higher and the product ratio is higher, and the application range is expanded.

The invention belongs to the technical field of image processing, and discloses a nail image coloring processing method and device. The method comprises the steps: obtaining a first hand image comprising nails; determining nail areas in the first hand image; performing image coloring processing on the nail areas to obtain a second hand image; and outputting/displaying the second hand image. The method can be used for detecting the nail areas in real time and coloring nails according to colors or patterns specified by a user, and has the advantages that the model is small, the speed is high, real-time detection and coloring can be achieved, and different nail beautifying experiences are brought to the user.

The invention belongs to the field of agricultural machinery, and particularly relates to a chemical fertilizer applicator which comprises a framework, a traction frame, rolling wheels, a fertilizer tank, a driving shaft, bearing blocks, a transmission shaft, a shifting shaft, shifting wheels, a first driving chain wheel, a first driven chain wheel, a second driving chain wheel, a second driven chain wheel, a first chain, a second chain, grooves, discharge pipes, furrowing plows and soil burying plates. The chemical fertilizer applicator has the advantages that the chemical fertilizer applicator is simple in structure and convenient to operate, is small, has diversified furrowing, fertilizer application and soil burying functions and is provided with the shifting wheels, and accordingly the fertilizer application rates can be accurately controlled; lands can be divided by the hollow furrowing plows with the adjustable depths and the adjustable widths, accordingly, fertilizers can flowinto underground environments along the furrowing plows, fertilizer application procedures can be completed, and the fertilizers can be buried by the rear hung soil burying plates; the lands and the root systems of original plants rarely can be destroyed by the chemical fertilizer applicator as compared with common fertilizer application modes, the chemical fertilizer applicator is provided with the conical fertilizer tank, accordingly, the fertilizers can automatically flow to the shifting wheels in hourglass flow modes, and chemical fertilizers at uniform flow velocities can be prevented from being retained.

The invention provides a Transform-based adaptive medical image classification method and system, and the method comprises the steps: obtaining basic image feature information through a convolutional neural network, transmitting the image feature information to a channel attention network structure, obtaining a weighted channel attention feature map, transmitting the channel attention feature map to a Transform network, and obtaining a weighted channel attention feature map; and finally, inputting the obtained feature vector into a full connection layer, and directly outputting a final classification result of the algorithm by the full connection layer. According to the method, the convolutional neural network and the Transform model are effectively combined together, so that the redundancy of the model is reduced, and the global context information of the image can be captured to extract powerful feature information.

The invention discloses multifunctional intelligent tableware. The multifunctional intelligent tableware comprises a tableware body and a food storage operating machine body arranged on an end face ofa top portion of the tableware body, an operation cavity with an opening facing upwards is formed in the food storage operating machine body, a machine cover is in power hinge joint with a top portion of the food storage operating machine body, a discharging hole is penetratingly formed in a wall of a top portion of the machine cover, a rotating disc is connected into the operation cavity in a rotating matched manner and is provided with a disk clamping hole which is circumferentially formed and positioned at the bottom of the discharging hole, a food storage disk is connected into the disk clamping hole in a rotating matched manner, a positioning sensor is arranged on the food storage disk, and a pusher positioned at the bottom of the discharging hole is embedded in an inner wall of a bottom portion of the operation cavity. The multifunctional intelligent tableware is simple in structure, intelligent, effective, small in size and convenient to operate, fetch and move.