52results about How to "Small target" patented technology

The invention discloses an improved weighting region matching high-altitude video pedestrian recognizing method (KS-WRM (KS-weighting matching region)). The improvement is reflected as follows: 1) confirming a candidate region by utilizing Kalman filtering; 2) fixing a camera or not by adopting different pedestrian detecting strategies; 3) proposing a pedestrian detecting method of an HLS (hue, lightness and saturation) model with multi-characteristic fusion; and 4) dividing pedestrians based on CA obvious region detection of context sensing. According to the invention, pedestrians can be recognized accurately under complex occasions of blur details, complex backgrounds, noise influences and the like. And the improved weighting region matching high-altitude video pedestrian recognizing method (KS-WRM) provided by the invention can be used for pedestrian detection and recognition at places with high visitor flow rate, such as remote sensing satellite images, malls, subway stations, railway stations, airports, as well as intelligent traffic control, intelligent vehicle auxiliary driving, pedestrian flow rate statistics and analysis places.

The present invention relates to an electromechanical integral equipment capable of utilizing bioligical information to control movement. It is characterized by utilizing various sensors to collect various biological informations and transferring these biological informations into central computer to control various drive elements. The transmission of signal can use wired, wireless and Internet transmission mode.

The invention belongs to the field of target identification in remote sensing image processing, provides an infrared remote sensing image ship detection method, and solves the problem that an existingdetection method based on artificial design features is complex in process, low in robustness, narrow in application range and the like and the problem that a large amount of missing detection and false detection exist due to small ship targets in a complex marine environment for a method based on deep learning infrared remote sensing images. According to the main scheme, the method comprises thesteps that an infrared remote sensing ship data set is created, offline data enhancement is conducted, and the data set is divided into a training set, a verification set and a test set; and the training set obtained by division is input into an improved RefineDet detection network to carry out training. The core of the detection network is a basic feature extraction network ResNet101 and a feature pyramid feature fusion module FPN combined with a visual saliency module CBAM. The detection process is a two-step cascade regression mode, the category recognition and position regression precision of ship targets can be improved, and a final ship target detection result can be obtained by outputting the category confidence coefficient and the regression frame after threshold filtering by thenetwork and performing non-maximum suppression.

A process for removing the anti-nutrition factor from soybean dregs by fermenting method includes providing raw soybean dregs, adding water, inoculating yeast, lactobacillus, Bacillus subtilis, etc, fermenting at 30-55 deg.C, and treating the finished product to obtain the feed of young animals.

A double-ship telescopic airbag type floating deck comprises a left ship, a right ship and a plurality of same telescopic airbag type floating bridges, wherein the left ship and the right ship are symmetrically distributed; the telescopic airbag type floating bridges are arranged between the left ship and the right ship; each telescopic airbag type floating bridge comprises a push rod mechanism, an upper rope mechanism, a lower rope mechanism, a swinging plate, a caterpillar band, a left airbag and a right airbag; the telescopic airbag type floating bridges are parallel to each other; the two ends of the telescopic airbag type floating bridges are connected with support plates of the left ship and the right ship; the push rod mechanisms comprise cylinder bodies, push rods and guide wheels; the swinging plates are rotationally connected with one side, close to the ship body, of the upper part of the support plate of the right ship; the upper rope mechanisms comprise upper ropes, electric motors and winding drums; the caterpillar bands comprise T-shaped frames and plate groups; the two ends of the upper parts of the T-shaped frames are rotationally connected with the left plate groups and the right plate groups, respectively; the two sides of the lower parts of the T-shaped frames are connected with one ends of the left airbags and the right airbags in a sealed way; and the other ends of the left airbags and the right airbags are connected with the support plates of the left ship and the right ship in a sealed way. The invention can be used as the water plane floating runway decks and floating bridges for carrying people and vehicles.

The invention provides a cloud printing realizing method based on cloud commerce modes. The method is characterized in that at first, all commercial printing systems and documental printing service systems are set into a public cloud printing system and a private cloud printing system, secondly, the public cloud printing system obtains the printing and documental printing service requirements made by individual clients or unit clients through the internet, thirdly, the public cloud printing system obtains all private cloud information through the internet, fourthly, the public cloud printing system utilizes the cloud computing technology for effectively dispatching all resources joining the private cloud printing system, fifthly, by means of client side software of the private cloud printing system, the private cloud printing system manages and dispatches all the printing equipment resources in the private cloud printing system in a centralized mode, counts the service condition and the work load condition of the resources of the private cloud printing system in real time, and feeds the service condition and the work load condition back to the public cloud printing system so that dispatch of the whole system can be optimized in real time and printing can be finished. The method is beneficial for increasing the utilization rate of the cloud printing equipment resources, and reducing the equipment number and the use cost.

The present invention relates to a novel interchangeable lockable catheter having a cap, the cap locking onto a junction hub or base, and encasing at least one lumen proximally to the junction hub of a multi-lumen catheter, PICC line and the like. The interchangeable lockable catheter's cap and base may be made of more than one piece, and provide a locking mechanism sufficient to deter tampering, while providing a low profile, comfortable, sanitary, and efficient means of closing off lumens for patients leaving the treatment area.

The invention relates to the technical field of unmanned aerial vehicles, and concretely to an air-ground multi-purpose unmanned aerial vehicle with three-axis tilting rotor wings and foldable wings,comprising an unmanned aerial vehicle body, a triphibian maneuvering mechanism used for providing power for the unmanned aerial vehicle body, a vector adjusting mechanism used for changing the vectordirection of the triphibian maneuvering mechanism, and a folding wing assembly used for adjusting the flight aerodynamic layout of the unmanned aerial vehicle. The triphibian maneuvering mechanism comprises a hub used for plane crawling and a rotor wing capable of flying in the air and sailing on the water surface. The folding wing assembly comprises a wing root, a wing tip, a first wing folding mechanism used for controlling the angle change of the wing root, and a second wing folding mechanism used for controlling the angle change of the wing tip. By changing tilting of the rotor wings, conversion of vertical take-off and landing, hovering and flying of the unmanned aerial vehicle can be rapidly achieved, meanwhile, the unmanned aerial vehicle can rapidly crawl and be adsorbed on the complex ground through the hubs, and tasks such as tracking, inspection, security and protection and patrol can be conveniently completed.

The present invention relates to isolated or purified or partially purified peptide derived molecules having the following general formula (S1): X-[(Pro)_n-His-Pro-His-Ala-Arg-Ile-Lys]_m-Y. The peptides are for medical use, in particular as anti-tumoral agents.

The invention discloses a micro unmanned aerial vehicle swarm combat system which comprises a plurality of micro unmanned aerial vehicles, a task processing terminal and a handheld control terminal. The weight of the whole miniature unmanned aerial vehicle is smaller than 100 g, and the miniature unmanned aerial vehicle internally comprises a flight control module, a flight power system, a GPS positioning module, an image recognition module and a link module. Through the technical scheme of the invention, the method has the advantages of portability and secrecy, provides an effective reconnaissance and strike means for individual combat under the condition of limited combat ability and endurance, ensures that personnel are prevented from directly fighting with enemies, reduces casualty risks, and effectively realizes the application of the miniature unmanned aerial vehicle swarm in individual combat.

The invention relates to application of a compound in preparation of drugs for resisting picornavirus. The compound can effectively inhibit the drugs for resisting picornavirus, has a good inhibitingeffect on human enterovirus 71 (EV-A71), can be used for treating various diseases caused by drugs for resisting picornavirus infection, is especially used for treating hand-foot-mouth disease, and isexpected to solve the dilemma that the hand-foot-mouth disease is not targeted clinically. In addition, the compound disclosed by the invention is derived from a natural extract and is high in safety.

The invention provides a traffic sign recognition model training method, a traffic sign recognition method and a traffic sign recognition device, and the traffic sign recognition method greatly avoids the detection time through the recognition characteristics of a single-stage detection algorithm in a deep learning neural network. According to the traffic sign recognition model training method, on the basis of an FCOS algorithm, the phenomenon of imbalance of positive and negative samples is reduced by introducing an attention mechanism CBAM; a swish function is introduced to avoid a certain degree of feature loss phenomenon; and features of different scales are protected through multi-scale feature fusion. According to the traffic sign recognition method, real-time detection and recognition of traffic signs in a real road scene can be realized, and the problems of small detection object target, natural environment interference, real-time recognition and the like in detection are solved.

The invention relates to a distance measuring method based on binocular fixed-focus cameras with different focal lengths. The method comprises the following steps: firstly, constructing a binocular distance measuring device; determining a calibration distance, calibrating a binocular overlapping region by taking the checkerboard as a reference object, judging the region where the temperature measurement target is located, performing distance calculation on a specific target in the binocular overlapping region based on a binocular imaging principle, and performing distance calculation on a specific target in a non-binocular overlapping region based on a triangular relationship. The distance measurement method has the advantages of high distance measurement precision, good robustness, low algorithm space time complexity, low occupied memory amount, short calculation time and the like; and the measurement range and the measurement distance of the binocular fixed-focus camera can be freelyconfigured and combined to be adjusted according to the focal length of the binocular fixed-focus camera, so that the equipment threshold of binocular distance measurement is reduced.

The invention relates to the field of fundus image processing, in particular to a fundus image micro-hemangioma automatic detection method and storage equipment. The fundus image micro-hemangioma automatic detection method comprises the steps of acquiring a fundus image to be analyzed; preprocessing the fundus image; establishing a multi-scale matched filtering operator; performing large-scale matched filtering on the preprocessed fundus image to remove background interference to obtain a micro-hemangioma candidate region; performing small-scale matched filtering on the preprocessed fundus image, and extracting a main blood vessel network; and performing morphological characteristic analysis on the micro-hemangioma candidate region to confirm the micro-hemangioma. The whole process does not need a large amount of data to carry out deep learning training, a doctor is simply, effectively and rapidly helped to exclude fundus photos without hemangioma or diabetic patients without DR, and the workload of further diagnosis and large-scale DR screening traditional Chinese medicine doctor interpretation grading is greatly reduced.

Provided is an individual assault panzer which is characterized by including an integrated combined panzer body, a digital operation platform, and a double-feet driving system. The digital operation platform is arranged in the integrated combined panzer body, observation aiming systems are embedded on the front side and the rear side of the panzer body, each observation aiming system includes an observation mirror, a low-light sighting telescope, a radar, and a laser range finder, the observation mirror at the front side of the panzer body can reflect the investigated image on the digital operation platform in the panzer body, weapons such as guns in automation setting in the panzer body are controlled to automatically follow the low-light sighting telescope to perform focusing and aiming in the whole process, and data analysis can be carried out by the laser range finder. An operator can directly send an order or transmits the order through the digital operation platform to a command set to analyze, and then the command set can give the corresponding order to the operator, and at the end, the double-feet driving system in the panzer body can operate and transfer the panzer, and makes the panzer drive by means of target homing, and operates the panzer to assault by double feet through the analysis of the digital operation platform based on the data of the observation aiming systems.

The invention discloses a training method, a translation method and a translation system for a sign language video translation model, and belongs to the field of pattern recognition and intelligent systems. The method comprises the following steps: firstly, preprocessing sign language video data in an isolated word data set, extracting a character region in a sign language video, detecting and tracking a moving hand by utilizing a Mask RCNN network model, extracting hand features by utilizing a first network module, and extracting human body features by utilizing a second network module; performing feature information fusion on the extracted hand features and human body features by using a full connection layer, and performing training to obtain a weight model of isolated words; taking theobtained weight model of the isolated word as a pre-training model of a third network module, and performing feature extraction on the continuous statement video by utilizing the third network module; and inputting an extraction result into an Seq2Seq model for training to obtain a trained sign language video translation model, and further proposing a translation method and a system architecture.The invention is good in sign language video translation effect and high in accuracy.

The invention discloses an application of palmatine for preparing medicine for treating and preventing West Nile virus infection; the palmatine to West Nile virus (WNV) has good inhibiting function, and the inhibition ratio of palmatine to the West Nile virus (WNV) is 97.71 percent respectively under the condition that the concentration of the palmatine is 100M, and the survival rate of Vero cells is 92.93 percent under the condition that the concentration of the palmatine is 100M. The palmatine can effectively inhibit West Nile virus, but has no cytotoxicity, therefore, the palmatine can be further developed into the medicine for treating diseases caused by West Nile virus infection and has wide application prospect.

The invention relates to a method of an efficient dynamic aldehyde-removal sterilization and odor-removal device. The device includes fan driving force units, efficient aldehyde-removal and sterilization units, and odor-removal and moisture absorption units, the fan driving force units include low power consumption miniature fans, polymer rechargeable batteries, and charge and discharge managementmodules, the efficient aldehyde-removal and sterilization units are provided with high-activity aldehyde-removal sterilizing agents, and the odor-removal and moisture absorption units are provided with multilayer activated carbon fibers and moisture absorbents. The dynamic aldehyde-removal sterilization and odor-removal device is used to blow air to be processed in a wardrobe, a drawer, and othernarrow space into the efficient aldehyde-removal and sterilization units though the miniature fans, the air after aldehyde-removal and sterilization enters into absorption and moisture absorption units, other macromolecule harmful gas can be absorbed by activated carbon, and meanwhile the humidity in air can be lowered. The device is provided with multiple effects of aldehyde-removal sterilization odor-removal and moisture-removal, and is convenient to use, and the effect is significant.

The invention discloses a fault-oriented safety transponder detection system. The system comprises a binocular camera and a light source which are arranged at the bottom of a train side by side with an antenna of a BTM, and a safety main processor connected with the binocular camera. Two cameras of the binocular camera are respectively arranged on two sides of the antenna of the BTM; the binocular camera collects real-time images from a transponder to steel rail sleepers on the two sides, the safety main processor carries out image feature extraction on the real-time images, the extracted image features match pre-configured pre-stored images, and the track and the transponder are recognized according to the matching result. The invention further discloses a transponder detection method. The transponder information reading scheme of the signal system can be greatly simplified, and the system safety is improved.