Simultaneous Localization and Mapping (SLAM) is considered significant for intelligent mobile robot autonomous pathfinding. Over the past years, many successful SLAM systems have been developed and works satisfactorily in static environments. However, in some dynamic scenes with moving objects, the camera pose estimation error would be unacceptable, or the systems even lose their locations. In this paper, we present SaD-SLAM, a visual SLAM system that, building on ORB-SLAM2, achieves excellent performance in dynamic environments. With the help of semantic and depth information, we find out feature points that belong to movable objects. And we detect whether those feature points are keeping still at the moment. To make the system perform accurately and robustly in dynamic scenes, we use both feature points extracted from static objects and static feature points derived from movable objects to finetune the camera pose estimation. We evaluate our algorithm in TUM RGB-D datasets. The results demonstrate the absolute trajectory accuracy of SaD-SLAM can be improved significantly compared with the original ORB-SLAM2. We also compare our algorithm with DynaSLAM and DS-SLAM, which are designed to fit dynamic scenes.

Conventional multiple-instance learning (MIL) algorithms for image annotation usually neglect concept dependence (i.e., the relationship between positive and negative concepts) and feature selection (i.e., which feature modality is suitable for a specific concept) problems, which have significant influence on the annotation performance. In this paper, we propose a novel concept-dependent algorithm for image annotation, named existence-based MIL (EBMIL), aiming at solving the above two problems in one scheme. In our EBMIL scheme, we give a new MIL formulation, named existence-based MIL, to explore the concept dependence in image annotation. Moreover, we give an optimization procedure in EBMIL, which is able to select different feature modalities for each concept under MIL settings. EBMIL achieves promising experimental results on the benchmark of COREL dataset with comparison to typical MIL algorithms.

A video genre categorization scheme based on SVM classifiers with active learning was proposed.The scheme consists of two steps: firstly,ten computable visual features related to video genres were analyzed and extracted;secondly,to acquire training samples for SVM classifiers,active learning was adopted to select the most informative samples for users to label.This can achieve comparable categorization accuracy with fewer training samples labeled.Moreover,to tackle the problem of selecting informative samples in the multi-class case,a new sample selection strategy was proposed.In this strategy,posterior probability was used to calculate the confidences of unlabeled samples.The informative samples were selected from the unlabeled samples according to their confidences.Experimental results show that active learning achieves good video genre categorization performance compared with the previous passive learning method,and active learning based on posterior probability performs better than the existing method based on version space.

Traditional Hough transform for circle detection has several limitations,such as high computation and memory complexity. To solve these problems,we presented a modified Hough transform method based on gradient information and fuzzy theory. First,gradient information was utilized to reduce the computational complexity. Furthermore,edge points were mapped based on fuzzy theory to avoid peak diffusion and false peak. Finally,a post-processing algorithm was designed to remove the false alarms,since Hough transform would neglect the connectivity between points. Experimental results show that the proposed method has many advantages,such as low computational complexity,high detection accuracy,high detection rate,and low false target rate.

Graph-based semi-supervised learning methods have been proven effective in tackling the difficulty of training data insufficiency in many practical applications such as video annotation. These methods are all based on an assumption that the labels of similar samples are close. However, as a crucial factor of these algorithms, the estimation of pairwise similarity has not been sufficiently studied. Usually, the similarity of two samples is estimated based on the Euclidean distance between them. But we will show that similarities are not merely related to distances but also related to the structures around the samples. It is shown that distance-based similarity measure may lead to high classification error rates even on several simple datasets. In this paper we propose a novel neighborhood similarity measure, which simultaneously takes into account both thse distance between samples and the difference between the structures around the corresponding samples. Experiments on synthetic dataset and TRECVID benchmark demonstrate that the neighborhood similarity is superior to existing distance based similarity.

Learning based semantic video annotation is a promising approach for enabling content-based video search. However, severe difficulties, such as insufficiency of training data and curse of dimensionality, are frequently encountered. This paper proposes a novel unified scheme, Optimized Multi-Graph-based Semi-Supervised Learning (OMG-SSL), to simultaneously attack these difficulties. Instead of only using a single graph, OMG-SSL integrates multiple graphs into a regularization and optimization framework to sufficiently explore their complementary nature. We then show that various crucial factors in video annotation, including multiple modalities, multiple distance metrics, and temporal consistency, in fact all correspond to different correlations among samples, and hence they can be represented by different graphs. Therefore, OMG-SSL is able to simultaneously deal with these factors within a unified framework. Experiments on the TRECVID benchmark demonstrate the effectiveness of our proposed approach.

This paper proposes a video semantic feature extraction approach based on multi-graph semi-supervised learning, which aims to simultaneously deal with the insufficiency of training data and the curse of dimensionality. In contrast to traditional graph-based semi-supervised learning, which generates graph from high-dimensional low-level features, we separate the original low-level features into multiple modalities with minimum correlations, and thus multiple graphs are obtained from these modalities. This way can tackle the curse of dimensionality brought by the high-dimensional feature space. We then propose a criterion to optimally fuse these graphs based on the pairwise relationships among training samples, and implement semi-supervised learning on the fused graph. Experimental results have demonstrated the effectiveness of the proposed approach.

In image retrieval, the concepts are usually in region-level but annotated in image-level, which leads to a major difficulty in learning the target concepts. In this paper, we formulate region-based image retrieval as a multiple-instance learning (MIL) problem, and propose an efficient and effective algorithm, named MI-AdaBoost, to solve it. The algorithm firstly maps each bag into a new bag feature space using a certain set of instance prototypes, and then adopts AdaBoost to select the bag features and build classifiers simultaneously. Experiments on both COREL and MUSK datasets show the proposed scheme is much more efficient than some typical existing MIL algorithms while has comparable results.

This paper describes the MSRA-USTC-SJTU experiments for TRECVID 2007. We performed the experiments in high-level feature extraction and automatic search tasks. For high-level feature extraction, we investigated the benefit of unlabeled data by semi-supervised learning, and the multi-layer (ML) multi-instance (MI) relation embedded in video by MLMI kernel, as well as the correlations between concepts by correlative multi-label learning. For automatic search, we fuse text, visual example, and concept-based models while using temporal consistency and face information for re-ranking and result refinement.

In this paper we discuss a typical case in video concept detection: to learn target concept using only a small number of positive samples. A novel manifold-ranking based scheme is proposed, which consists of three major components: feature pool construction, pre-filtering, and manifold-ranking. First, as there are large variations in the effective features for different concepts, a large feature pool is constructed, from which the most effective features can be selected automatically or semi-automatically. Second, to tackle the issue of large computation cost for successive manifold-ranking process when large video database is incorporated, we employ a pre-filtering process to filter out the majority of irrelevant samples while retaining the most relevant ones. And last, the manifold-ranking algorithm is used to explore the relationship among all of the rest samples based on the selected features. This scheme is extensible and flexible in terms of adding new features into the feature pool, introducing human interactions on selecting features, and defining new concepts.

Insufficiency of labeled training data is a major obstacle for automatically annotating large-scale video databases with semantic concepts. Existing semi-supervised learning algorithms based on parametric models try to tackle this issue by incorporating the information in a large amount of unlabeled data. However, they are based on a "model assumption" that the assumed generative model is correct, which usually cannot be satisfied in automatic video annotation due to the large variations of video semantic concepts. In this paper, we propose a novel semi-supervised learning algorithm, named Semi Supervised Learning by Kernel Density Estimation (SSLKDE), which is based on a non-parametric method, and therefore the "model assumption" is avoided. While only labeled data are utilized in the classical Kernel Density Estimation (KDE) approach, in SSLKDE both labeled and unlabeled data are leveraged to estimate class conditional probability densities based on an extended form of KDE. We also investigate the connection between SSLKDE and existing graph-based semi-supervised learning algorithms. Experiments prove that SSLKDE significantly outperforms existing supervised methods for video annotation.

This paper presents an automatic video genre categorization scheme based on the hierarchical ontology on video genres. Ten computable spatio-temporal features are extracted to distinguish the different genres using a hierarchical support vector machines (SVM) classifier built by cross-validation, which consists of a series of SVM classifiers united in a binary-tree form. As the order and genre partition strategy of the SVM classifier series affect the over performance of the united classifier, two optimal SVM binary trees, local and global, are constructed aiming at finding the best categorization orders, i.e., the best tree structure, of the genre ontology. Experimental results show that the proposed scheme outperforms C4.5 decision tree, typical 1-vs-1 SVM scheme, as well as the hierarchical SVM built by K-means.