Lightweight Human Behavior Recognition Method for Visual Communication AGV Based on CNN-LSTM

To improve traditional video surveillance systems' performance on human behavior recognition, a new system has been built. Not visual camera but depth camera is chosen as sensor. To adapt to the most common forward oblique view of camera, a normalized digital elevation map, whose pixel intensity indicates the elevation of the scene, is built from the depth image. Coordinates and intensity in the digital elevation map represent the position information about the scene. Oriented templates are proposed to match and detect the human head robustly in the elevation map. As for the excellent visibility of human head in the elevation map, we track the human head to get trajectory. By combining the trajectory information of human head with the elevation map, several predefined human behaviors are recognized. Our behavior recognition method is straightforward and robust. This uniqueness has no similar with the traditional machine learning and classification framework about human behavior recognition.

With the rapid development of 3D somatosensory technology, human behavior recognition has become an important research field. Human behavior feature analysis has evolved from traditional 2D features to 3D features. In order to improve the performance of human activity recognition, a human behavior recognition method is proposed, which is based on a hybrid texture-edge local pattern coding feature extraction and integration of RGB and depth videos information. The paper mainly focuses on background subtraction on RGB and depth video sequences of behaviors, extracting and integrating historical images of the behavior outlines, feature extraction and classification. The new method of 3D human behavior recognition has achieved the rapid and efficient recognition of behavior videos. A large number of experiments show that the proposed method has faster speed and higher recognition rate. The recognition method has good robustness for different environmental colors, lightings and other factors. Meanwhile, the feature of mixed texture-edge uniform local binary pattern can be used in most 3D behavior recognition.

Vision-based behavior recognition is the analysis and recognition of human behavior in video. It has been widely used in many aspects such as multimedia information retrieval, behavior monitoring, and robot perception. This paper uses the Independent Subspace Analysis (ISA) deep network model feature extraction method, which is based on the ISA model and neural network theory, and combines data preprocessing methods, [Formula: see text]-means clustering methods, and Support Vector Machine (SVM) classifiers to achieve video classification and identification of human behavior. The ISA-based deep network model feature extraction method is an unsupervised learning method that can obtain behavior characteristics with good invariance and characterization capabilities in video human behavior. The experiment was conducted on the basis of the Hollywood2 human behavior data set. This experiment was compared with other commonly used human behavior feature extraction and recognition methods. The experimental results validated the effectiveness and advantages of this method in the classification and recognition of human behavior.

Aiming at the low accuracy of behavior recognition technology for multi-target human behavior recognition in small and medium scenes, a method for multi-target human behavior recognition in small and medium scenes is proposed. In this paper, YOLOv5 and DeepSort are used to detect, track and locate human targets in the video stream. According to the detection frame, the appropriate size of the human target is cropped as the input image of the behavior recognition module to reduce the interference of human behavior background, and finally realize the multi-target human body behavior recognition. The behavior recognition module is composed of an improved C3D network, and the features extracted by YOLOv5 are shared with the behavior recognition module to reduce the amount of computation. Experiments show that this method achieves end-to-end recognition,and can recognize the behavior of different target human bodies in small and medium scenes, and achieves comparable results.

Human behavior recognition model based on improved EfficientNet

Aiming at the problem that the existing human skeleton behavior recognition methods are insensitive to human local movements and show inaccurate recognition in distinguishing similar behaviors, a multi-scale spatio-temporal graph convolution method incorporating multi-granularity features is proposed for human behavior recognition. Firstly, a skeleton fine-grained partitioning strategy is proposed, which initializes the skeleton data into data streams of different granularities. An adaptive cross-scale feature fusion layer is designed using a normalized Gaussian function to perform feature fusion among different granularities, guiding the model to focus on discriminative feature representations among similar behaviors through fine-grained features. Secondly, a sparse multi-scale adjacency matrix is introduced to solve the bias weighting problem that amplifies the multi-scale spatial domain modeling process under multi-granularity conditions. Finally, an end-to-end graph convolutional neural network is constructed to improve the feature expression ability of spatio-temporal receptive field information and enhance the robustness of recognition between similar behaviors. The feasibility of the proposed algorithm was verified on the public behavior recognition dataset MSR Action 3D, with a accuracy of 95.67%, which is superior to existing behavior recognition methods.

With the popularity of wearable devices, human behavior recognition technology is becoming increasingly important in social surveillance, health monitoring, smart home, and traffic management. However, traditional human behavior recognition methods rely too much on the subjective experience of managers in hyperparameter selection, resulting in an inefficient parameter optimization process. To address this problem, this paper proposes a long short–term memory (LSTM) neural network model based on a subtraction‐average–based optimizer (SABO) for human behavior recognition in wearable devices. Compared to the traditional method, the SABO–LSTM model significantly improves the recognition accuracy by automatically finding the optimal hyperparameters, which proves its innovation and superiority in practical applications. To demonstrate the effectiveness of the method, four evaluation metrics, including F1 score, precision, recall, and accuracy, are used to validate it on the UCI‐HAR dataset and the WISDM dataset, and control groups are introduced for comparison. The experimental results show that SABO–LSTM can accurately perform the human behavior recognition task with an accuracy of 98.84% and 96.37% on the UCI‐HAR dataset and the WISDM dataset, respectively. In addition, the experimental model outperforms the control model on all four evaluation metrics and outperforms existing recognition methods in terms of accuracy.

Human behavior analysis is a hot research in the field of computer vision. It has broad application prospects in the fields of intelligent monitoring, human-computer interaction, motion analysis and virtual reality. In order to improve the accuracy of human behavior recognition, a human behavior recognition method based on HOG feature and SVM classifier is proposed. First, the HOG features of the training set and the test set are extracted. Then, the multi-class problem is transformed into multiple dual-class problems, and multiple SVM classifiers are trained by using the HOG features. Finally, the trained classifiers are employed to recognize the human walking and waving behavior. Experimental results show that the recognition rate of walking and waving is 87.5% for the UIUC database. The human behavior recognition method proposed in this paper can effectively improve the recognition rate.

The traditional human motion perception and behavior recognition methods are based on machine vision and image processing. This method has the disadvantages of strong intrusion of individual data privacy, large environmental impact and tedious data processing, and cannot meet the practical requirements in real time. This paper introduced a solution of accurately capture human motion by using multi-sensor of MEMS to construct Zigbee wireless network, and utilizing SVM classification algorithm to realize human action recognition efficiently. The system is used to detect the abnormal human fall behavior, which is perfect reliability and real-time performance and the recognition accuracy of the action is above to 90%.

3D Human behavior recognition based on binocular vision and face–hand feature

The accurate analysis of human dynamic behavior is very important for overcoming the limitations of movement diversity and behavioral adaptability. In this paper, a wearable device-based human dynamic behavior recognition method is proposed. The method collects acceleration and angular velocity data through a six-axis sensor to identify information containing specific behavior characteristics in a time series. A human movement data acquisition platform, the DMP attitude solution algorithm, and the threshold algorithm are used for processing. In this experiment, ten volunteers wore wearable sensors on their bilateral forearms, upper arms, thighs, calves, and waist, and movement data for standing, walking, and jumping were collected in school corridors and laboratory environments to verify the effectiveness of this wearable human movement recognition method. The results show that the recognition accuracy for standing, walking, and jumping reaches 98.33%, 96.67%, and 94.60%, respectively, and the average recognition rate is 96.53%. Compared with similar methods, this method not only improves the recognition accuracy but also simplifies the recognition algorithm and effectively saves computing resources. This research is expected to provide a new perspective for the recognition of human dynamic behavior and promote the wider application of wearable technology in the field of daily living assistance and health management.

The key problem in human behavior recognition is how to build a spatiotemporal feature extraction and classification network. Aiming at the problem that the existing channel attention mechanism directly pools the global average information of each channel and ignores its local spatial information, this paper proposes two improved channel attention modules, namely the space-time (ST) interaction module of matrix operation and the depth separable convolution module, combined with the research of human behavior recognition. Combined with the superior performance of convolutional neural network (CNN) in image and video processing, a multi-scale convolutional neural network method for human behavior recognition is proposed. Firstly, the behavior video is segmented, and low rank learning is performed on each video segment to extract the corresponding Low rank behavior information, and then these Low rank behavior information are connected on the time axis to obtain the Low rank behavior information of the whole video, so as to effectively capture the behavior information in the video, avoiding tedious extraction steps and various assumptions. The ability of neural network to model human behavior can be transferred and reused in networks with different structures. According to the different characteristics of data features at different network levels, two effective feature difference measurement functions are introduced to reduce the difference between features extracted from different network structures. Experiments on several public datasets show that the proposed method has a good classification effect. The experimental results show that the method has a good accuracy in human behavior recognition. It is proved that the proposed model not only improves the recognition accuracy, but also effectively reduces the computational complexity of output weights and improves the compactness of the model structure.

t has been shown that the traditional seven Hu invariant moment does not have scaling invariance with low recognition rate in human behavior recognition. In order to improve the recognition rate, a human behavior recognition method will be put forward in this paper based on weighted modified Hu moments. Firstly, the traditional seven Hu moments will be extended to ten Hu moments to get more image details. Then, the extended Hu moments will be modified to make the Hu moments has the feature of scaling invariance. Lastly, the weighted modified Hu moment will be obtained through least squares method based on minimum variance criterion. The simulation of the sequence images shows that the weighted modified Hu moment can improve the recognition rate effectively.

This chapter describes a new human behavior recognition method based on Hidden Markov Models (HMM). We use a feature-based bottom-up approach using HMM, which can provide a learning capability and time-scale invariability. To apply HMM to our aim, time sequential images are transformed to an image feature vector sequence, and the sequence is converted to a symbol sequence by Vector Quantization. In learning human behavior categories, the model parameters of HMM are optimized so as to best describe training sequences. For recognition, the model that best matches the observed sequence is chosen. A new VQ method and HMM configuration for behavior recognition is proposed and evaluated. Experimental results of real time-sequential images of sports scenes show a higher than 90% recognition rate. We also describe an example application of this behavior recognition method to content-based video database retrieval.

Improved 1D-CNNs for behavior recognition using wearable sensor network