Lianwen Jin

Activity recognition from acceleration data based on discrete consine transform and SVM

This paper developed a high-accuracy human activity recognition system based on single tri-axis accelerometer for use in a naturalistic environment. This system exploits the discrete cosine transform (DCT), the Principal Component Analysis (PCA) and Support Vector Machine (SVM) for classification human different activity. First, the effective features are extracted from accelerometer data using DCT. Next, feature dimension is reduced by PCA in DCT domain. After implementing the PCA, the most invariant and discriminating information for recognition is maintained. As a consequence, Multi-class Support Vector Machines is adopted to distinguish different human activities. Experiment results show that the proposed system achieves the best accuracy is 97.51%, which is better than other approaches.

Person Re-Identification by Regularized Smoothing KISS Metric Learning

With the rapid development of the intelligent video surveillance (IVS), person re-identification, which is a difficult yet unavoidable problem in video surveillance, has received increasing attention in recent years. That is because computer capacity has shown remarkable progress and the task of person re-identification plays a critical role in video surveillance systems. In short, person re-identification aims to find an individual again that has been observed over different cameras. It has been reported that KISS metric learning has obtained the state of the art performance for person re-identification on the VIPeR dataset . However, given a small size training set, the estimation to the inverse of a covariance matrix is not stable and thus the resulting performance can be poor. In this paper, we present regularized smoothing KISS metric learning (RS-KISS) by seamlessly integrating smoothing and regularization techniques for robustly estimating covariance matrices. RS-KISS is superior to KISS, because RS-KISS can enlarge the underestimated small eigenvalues and can reduce the overestimated large eigenvalues of the estimated covariance matrix in an effective way. By providing additional data, we can obtain a more robust model by RS-KISS. However, retraining RS-KISS on all the available examples in a straightforward way is time consuming, so we introduce incremental learning to RS-KISS. We thoroughly conduct experiments on the VIPeR dataset and verify that 1) RS-KISS completely beats all available results for person re-identification and 2) incremental RS-KISS performs as well as RS-KISS but reduces the computational cost significantly.

Activity recognition from acceleration data using AR model representation and SVM

In this paper, the autoregressive (AR) model of time-series is presented to recognize human activity from a tri-axial accelerometer data. Four orders of autoregressive model for accelerometer data is built and the AR coefficients are extracted as features for activity recognition. Classification of the human activities is performed with support vector machine (SVM). The average recognition results for four activities (running, still, jumping and walking) using the proposed AR-based features are 92.25%, which are better than using traditional frequently used time domains features (mean, standard deviation, energy and correlation of acceleration data) and FFT features. The results show that AR coefficients obvious discriminate different human activities and it can be extract as an effective feature for the recognition of accelerometer date.

Building compact MQDF classifier for large character set recognition by subspace distribution sharing

Quadratic classifier with modified quadratic discriminant function (MQDF) has been successfully applied to recognition of handwritten characters to achieve very good performance. However, for large category classification problem such as Chinese character recognition, the storage of the parameters for the MQDF classifier is usually too large to make it practical to be embedded in the memory limited hand-held devices. In this paper, we aim at building a compact and high accuracy MQDF classifier for these embedded systems. A method by combining linear discriminant analysis and subspace distribution sharing is proposed to greatly compress the storage of the MQDF classifier from 76.4 to 2.06MB, while the recognition accuracy still remains above 97%, with only 0.88% accuracy loss. Furthermore, a two-level minimum distance classifier is employed to accelerate the recognition process. Fast recognition speed and compact dictionary size make the high accuracy quadratic classifier become practical for hand-held devices.

Principal Component 2-D Long Short-Term Memory for Font Recognition on Single Chinese Characters

Chinese character font recognition (CCFR) has received increasing attention as the intelligent applications based on optical character recognition becomes popular. However, traditional CCFR systems do not handle noisy data effectively. By analyzing in detail the basic strokes of Chinese characters, we propose that font recognition on a single Chinese character is a sequence classification problem, which can be effectively solved by recurrent neural networks. For robust CCFR, we integrate a principal component convolution layer with the 2-D long short-term memory (2DLSTM) and develop principal component 2DLSTM (PC-2DLSTM) algorithm. PC-2DLSTM considers two aspects: 1) the principal component layer convolution operation helps remove the noise and get a rational and complete font information and 2) simultaneously, 2DLSTM deals with the long-range contextual processing along scan directions that can contribute to capture the contrast between character trajectory and background. Experiments using the frequently used CCFR dataset suggest the effectiveness of PC-2DLSTM compared with other state-of-the-art font recognition methods.

Person Reidentification by Minimum Classification Error-Based KISS Metric Learning

In recent years, person reidentification has received growing attention with the increasing popularity of intelligent video surveillance. This is because person reidentification is critical for human tracking with multiple cameras. Recently, keep it simple and straightforward (KISS) metric learning has been regarded as a top level algorithm for person reidentification. The covariance matrices of KISS are estimated by maximum likelihood (ML) estimation. It is known that discriminative learning based on the minimum classification error (MCE) is more reliable than classical ML estimation with the increasing of the number of training samples. When considering a small sample size problem, direct MCE KISS does not work well, because of the estimate error of small eigenvalues. Therefore, we further introduce the smoothing technique to improve the estimates of the small eigenvalues of a covariance matrix. Our new scheme is termed the minimum classification error-KISS (MCE-KISS). We conduct thorough validation experiments on the VIPeR and ETHZ datasets, which demonstrate the robustness and effectiveness of MCE-KISS for person reidentification.

Weightlessness feature — a novel feature for single tri-axial accelerometer based activity recognition

In this paper, a novel weightlessness feature for activity recognition from a tri-axial acceleration signals have been proposed. Since the orientation between accelerometer and userpsilas body may continuously change when user perform activities, we propose an algorithm to calibrate the actual vertical direction of accelerometer signal through estimating the gravitational direction. We combine peaks of signal and weightlessness feature to produce six dimensional weightlessness-based features for activity recognition. Classification of the activities is performed with Support Vector Machine (SVM). The average accuracy of four activities using the proposed weightlessness-based features is 97.21%, which are better than using traditional widely used time-domains features (mean, standard deviation, energy and correlation of acceleration data). Experimental results show that the new features can be used to effectively recognize different human activities and they are robust for different location of accelerometer.

Rank Preserving Sparse Learning for Kinect Based Scene Classification

With the rapid development of the RGB-D sensors and the promptly growing population of the low-cost Microsoft Kinect sensor, scene classification, which is a hard, yet important, problem in computer vision, has gained a resurgence of interest recently. That is because the depth of information provided by the Kinect sensor opens an effective and innovative way for scene classification. In this paper, we propose a new scheme for scene classification, which applies locality-constrained linear coding (LLC) to local SIFT features for representing the RGB-D samples and classifies scenes through the cooperation between a new rank preserving sparse learning (RPSL) based dimension reduction and a simple classification method. RPSL considers four aspects: 1) it preserves the rank order information of the within-class samples in a local patch; 2) it maximizes the margin between the between-class samples on the local patch; 3) the L1-norm penalty is introduced to obtain the parsimony property; and 4) it models the classification error minimization by utilizing the least-squares error minimization. Experiments are conducted on the NYU Depth V1 dataset and demonstrate the robustness and effectiveness of RPSL for scene classification.

Optimized graph-based segmentation for ultrasound images

Segmentation of medical images is an inevitable image processing step for computer-aided diagnosis. Due to complex acoustic inferences and artifacts, accurate extraction of breast lesions in ultrasound images remains a challenge. Although there have been many segmentation techniques proposed, the performance often varies with different image data, leading to poor adaptability in real applications. Intelligent computing techniques for adaptively learning the boundaries of image objects are preferred. This paper focuses on optimization of a previously documented method called robust graph-based (RGB) segmentation algorithm to extract breast tumors in ultrasound images more adaptively and accurately. A novel technique named as parameter-automatically optimized robust graph-based (PAORGB) image segmentation method is accordingly proposed and performed on breast ultrasound images. A particle swarm optimization algorithm is incorporated with the RGB method to achieve optimal or approximately optimal parameters. Experimental results have shown that the proposed technique can more accurately segment lesions from ultrasound images compared to the RGB and two conventional region-based methods.

A naturalistic 3D acceleration-based activity dataset & benchmark evaluations

In this paper, a naturalistic 3D acceleration-based activity dataset, the SCUT-NAA dataset, is created to assist researchers in the field of acceleration-based activity recognition and to provide a standard dataset for comparing and evaluating the performance of different algorithms. The SCUT-NAA dataset is the first publicly available 3D acceleration-based activity dataset and contains 1278 samples from 44 subjects (34 males and 10 females) collected in naturalistic settings with only one tri-axial accelerometer located alternatively on the waist belt, in the trousers pocket, and in the shirt pocket. Each subject was asked to perform ten activities. Benchmark evaluations of the dataset are provided based on FFT coefficients, DCT coefficients, time-domain features, and AR coefficients for the different accelerometer locations.