The invention provides a man-machine recognition method and device and a behavior characteristic data collecting method and device. The man-machine recognition method includes the steps that responding the man-machine recognition request sent by a client side, first operation used for man-machine recognition is rendered to be sent to the client side for displaying; second operation which is submitted by the client side and triggered by operation track represented by the first operation is received; according to a preset behavior characteristic model, man-machine recognition is carried out on a triggering body of the second operation. In the embodiment, accuracy of human-machine recognition can be improved, and user experience in the man-machine recognition process can be improved.

Man-machine recognition method and device and behavior characteristic data collecting method and device

The present invention provides a people counting method and device. The method is applied to a server building a people counting model comprising an image feature extraction sub model and an SSD classification regression sub model, and concretely comprises the steps of: inputting image frames into the image feature extraction sub model to generate an image feature graph; generating the default frame of each pixel point in the image feature graph based on the SSD classification regression sub model, obtaining the position coordinates and the probability score of each default frame, and taking the maximum probability score as a primary confidence coefficient; screening out front K default frames with the highest primary confidence coefficients as target candidate frames; performing boundingbox regression analysis and softxmax classification based on the position coordinates and the probability score of each default frame, and obtaining the coordinate position and the final confidence coefficient of each target candidate frame; and based on the non-maxima suppression algorithm, obtaining target frames, and performing statistics of the number of people in a monitoring area based on the quantity of the target frames. The method can effectively improve the timeliness of people counting.

People counting method and device

As a research hotspot in the field of human-machine interaction, a great progress of hand gesture recognition has been achieved with the development of deep learning of neural networks. However, in the deep learning based recognition methods, it is necessary to rely heavily on large-scale labeled dataset which is very hard to build in practical applications. In order to achieve a well performance under some strict constraint of few sample data, one-shot learning gesture recognition is studied and a joint deep training method by combination of 3D ResNet with a memory module is presented in this paper. In our scheme a combinatorial optimization of feature extraction by 3D ResNet with memory capacity of rare event by memory module is carried out with an effective strategy of optimal decision and two relative performance indices. In order to implement one-shot learning gesture recognition, the memory module is employed to remember the features extracted by well-trained 3D ResNet and the classification decision is performed by the nearest neighbor algorithm with cosine similarity measure. In view of real-world applications about human-machine interaction technology, its ability to deal with negative samples plays a significant role thus a mechanism based on the threshold of cosine similarity is built to realize effective classification and rejection respectively. In order to validate and evaluate the performance of our proposed method, a special hand gesture dataset containing 3045 gesture videos is built and a series of experiment results on our collected dataset and public datasets demonstrate the feasibility and effectiveness of our method.

One-shot learning gesture recognition based on joint training of 3D ResNet and memory module

The embodiment of the invention provides a control method, device, equipment and unmanned aerial vehicle. The method includes the steps of: obtaining attitude parameters of a holder (13) of an unmanned aerial vehile (12); and adjusting the attitude parameters of the unmanned aerial vehicle (12) according to the attidue parameters of the holder (14). The attitude parameters of the unmanned aerial vehicle passively change as the attitude parameters of the holder (14) change, thereby enriching the control mode of the holer (14), improving the flexibility of the control mode of the holder (14), and enabling the attitude adjustment of the holder (14) not to lag compared with the attitude adjustment of a fuselage of the unmanned aerial vehicle (12); and the problem of overshoot of the holder (14) that is possible to occur under an inertia effect is also avoided, thus the holder (14) can rotate more stably and stop rotating, the stability of shooting equipment (15) on the holder is ensured, and the stability of shot pictures of the shooting equipment (15) is improved.

Control method, device, equipment and unmanned aerial vehicle

Isolated Sign Language Recognition with Depth Cameras

The invention relates to a mobile robot control system based on a smart phone. According to the control system, one smart phone, i.e. an onboard smart phone, is used as a core controller; the onboard smart phone is a server side and is fixed on a machine body of a mobile robot; interaction with the onboard smart phone is carried out by a wireless communication module, a control instruction is received and transmitted, and other applications are associated and called to achieve control on the mobile robot; the other smart phone, i.e. a remote control smart phone, is used as a remote controller; and the remote control smart phone is a client, interacts with the onboard smart phone by a wireless communication module, and sends the control instruction to the server side after selecting a control mode. The mobile robot control system enables the mobile robot to be more convenient and rapid to debug, does not need to be connected with a PC (Personal Computer) machine each time to burn a program, becomes an ideal platform of verifying various control algorithms, and enables the mobile robot to have more powerful functions and become more intelligent; and the diversity of the remote control operation enables a human-computer interaction experience friendly degree to be greatly improved.

Mobile robot control system based on smart phone

Special human body recognition method based on head and shoulder model

The invention relates to a handwriting digital recognition method based on improved distance core principal component analysis, and belongs to the field of pattern recognition and artificial intelligence The handwriting digital recognition method is characterized in that an MNIST data base is used as a test object, a sample is first subjected to binaryzation preprocessing, processed sample data are mapped to a core feature space through a distance core, a K mean value cluster is used for dividing a training sample set into N kinds of secondary sets in the core feature space, then the feature vector of a core matrix in a core space to acquire a transformational matrix which is used for feature extraction, an extracted feature data set is put into a support vector machine to establish a training model, and finally the model is used for forecasting recognition rate of test samples According to the handwriting digital recognition method, handwriting digital recognition rate can be well improved, operation time is lowered, and the problem that a large sample is large in computing cost is solved

Handwriting digital recognition method based on improved distance core principal component analysis

Noise and constant empirical motion constraints affect the extraction of distinctive spatiotemporal features from one or a few samples per gesture class. To tackle these problems, an adaptive local spatiotemporal feature (ALSTF) using fused RGB-D data is proposed. First, motion regions of interest (MRoIs) are adaptively extracted using grayscale and depth velocity variance information to greatly reduce the impact of noise. Then, corners are used as keypoints if their depth, and velocities of grayscale and of depth meet several adaptive local constraints in each MRoI. With further filtering of noise, an accurate and sufficient number of keypoints is obtained within the desired moving body parts (MBPs). Finally, four kinds of multiple descriptors are calculated and combined in extended gradient and motion spaces to represent the appearance and motion features of gestures. The experimental results on the ChaLearn gesture, CAD-60 and MSRDailyActivity3D datasets demonstrate that the proposed feature achieves higher performance compared with published state-of-the-art approaches under the one-shot learning setting and comparable accuracy under the leave-one-out cross validation.

https://www.mdpi.com/1424-8220/16/12/2171/pdf

Adaptive Local Spatiotemporal Features from RGB-D Data for One-Shot Learning Gesture Recognition

The invention discloses a small-size aircraft system based on a cradle head, comprising a rack, a sensor box, a cradle head rolling rudder, a cradle head pitching rudder, a cradle head outer framework, a cradle head inner framework, an upper airscrew, a lower airscrew, an upper airscrew drive motor, a lower airscrew drive motor, a control unit, a telescopic rod and a pod. The aircraft system can realize complete control on the pose of an aircraft by pose adjustment on the cradle head and control on the revolving speed of the airscrews; the yaw angle of an aircraft body is controlled by reaction torque which is generated by the differential rotation of the upper and lower airscrews; the pitching angle and the rolling angle of the airscrews are realized by the rudders driving the cradle head to rotate; control on a spatial position is realized by the airscrew drive motors and pose adjustment on the cradle head. The small-size aircraft system is simple and reliable in design, and clear and explicit in structure; while expanding the existing rotor-type flight structure and control schemes, the small-size aircraft system is also a superior space carrier vehicle, and has considerable practical value.

Small-size aircraft system based on cradle head

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Lin Jia

Author Tools

Chat about Author