Jianfeng Lu

Hierarchical initialization approach for K-Means clustering

A hierarchical initialization approach is proposed to the K-Means clustering problem. The core of the proposed method is to treat the clustering problem as a weighted clustering problem so as to find better initial cluster centers based on the hierarchical approach. The experimental results show that the proposed approach needs less iteration time compared with existing approaches and has better performance in terms of convergence speed and ability to reduce the impact of noises.

Density-based hierarchical clustering for streaming data

For streaming data that arrive continuously such as multimedia data and financial transactions, clustering algorithms are typically allowed to scan the data set only once. Existing research in this domain mainly focuses on improving the accuracy of clustering. In this paper, a novel density-based hierarchical clustering scheme for streaming data is proposed in order to improve both accuracy and effectiveness; it is based on the agglomerative clustering framework. Traditionally, clustering algorithms for streaming data often use the cluster center to represent the whole cluster when conducting cluster merging, which may lead to unsatisfactory results. We argue that even if the data set is accessed only once, some parameters, such as the variance within cluster, the intra-cluster density and the inter-cluster distance, can be calculated accurately. This may bring measurable benefits to the process of cluster merging. Furthermore, we employ a general framework that can incorporate different criteria and, given the same criteria, will produce similar clustering results for both streaming and non-streaming data. In experimental studies, the proposed method demonstrates promising results with reduced time and space complexity.

Learning arbitrary-shape object detector from bounding-box annotation by searching region-graph

Location positiveness is proposed to encode the information of bounding box.Two graph methods are proposed to train region model from bonding-box annotation.Density ratio estimation is introduced to compute region weight for ERS. Arbitrary-shape is argued more precise than bounding-box for object detection. However, an arbitrary-shape detector usually requires pixel-level human annotation, which is very expensive and hardly afforded for any real-world application. On the other hand, bounding-box is much easier than pixel-wise segmentation in human labeling. In this paper we aim to realize the arbitrary-shape detection from bounding-box human annotation. To this end, we propose location positiveness, which encodes the information of bounding-box annotation to help obtain region annotation. In addition, we propose two graph-based methods to embed the location positiveness, which enable more accurate model trained from simpler annotation. Experimental results validate the performance of our method.

Road detection based on the fusion of Lidar and image data

In this article, we propose a road detection method based on the fusion of Lidar and image data under the framework of conditional random field. Firstly, Lidar point clouds are projected into the monocular images by cross calibration to get the sparse height images, and then we get high-resolution height images via a joint bilateral filter. Then, for all the training image pixels which have corresponding Lidar points, we extract their features from color image and Lidar point clouds, respectively, and use these features together with the location features to train an Adaboost classifier. After that, all the testing pixels are classified into road or non-road under a conditional random field framework. In this conditional random field framework, we use the scores computed from the Adaboost classifier as the unary potential and take the height value of each pixel and its color information into consideration together for the pairwise potential. Finally, experimental tests have been carried out on the KITTI Road data set, and the results show that our method performs well on this data set.

Maximum Likelihood Estimation of Monocular Optical Flow Field for Mobile Robot Ego-motion

This paper presents an optimized scheme of monocular ego-motion estimation to provide location and pose information for mobile robots with one fixed camera. First, a multi-scale hyper-complex wavelet phase-derived optical flow is applied to estimate micro motion of image blocks. Optical flow computation overcomes the difficulties of unreliable feature selection and feature matching of outdoor scenes; at the same time, the multi-scale strategy overcomes the problem of road surface self-similarity and local occlusions. Secondly, a support probability of flow vector is defined to evaluate the validity of the candidate image motions, and a Maximum Likelihood Estimation (MLE) optical flow model is constructed based not only on image motion residuals but also their distribution of inliers and outliers, together with their support probabilities, to evaluate a given transform. This yields an optimized estimation of inlier parts of optical flow. Thirdly, a sampling and consensus strategy is designed to estimate the ego-motion parameters. Our model and algorithms are tested on real datasets collected from an intelligent vehicle. The experimental results demonstrate the estimated ego-motion parameters closely follow the GPS/INS ground truth in complex outdoor road scenarios.

Calibration of medical x-ray apparatus with deformation

Calibration of the x-ray apparatus is necessary for many applications. Most of the literature on the calibration of x-ray apparatus seem to ignore the imaging deformation. Our main concern is how to apply Tsais nonlinear camera calibration technique to the calibration of a medical x-ray apparatus with deformation. In order to achieve this goal, two key problems should be solved: The first is how to calibrate some key intrinsic parameters, namely, the imaging center and sampling step of the detector, which are usually provided by the camera manufacturer but are unknown for the x-ray apparatus. The second is how to model the serious imaging deformation. Some practical schema are designed to solve these two problems, and the whole calibration procedure and experimental results are presented.