Mask-guided matting networks have achieved significant improvements and have shown great potential in practical applications in recent years. However, simply learning matting representation from synthetic and lack-of-real-world-diversity matting data, these approaches tend to overfit low-level details in wrong regions, lack generalization to objects with complex structures and real-world scenes such as shadows, as well as suffer from interference of background lines or textures. To address these challenges, in this paper, we propose a novel auxiliary learning framework for mask-guided matting models, incorporating three auxiliary tasks: semantic segmentation, edge detection, and background line detection besides matting, to learn different and effective auxiliary representations from different types of data and annotations. Our framework and model introduce the following key aspects: 1) to learn real-world adaptive semantic representation for objects with diverse and complex structures under real-world scenes, we introduce extra semantic segmentation and edge detection tasks on more diverse real-world data with segmentation annotations; 2) to avoid overfitting on low-level details, we propose a module to utilize the inconsistency between learned segmentation and matting representations to regularize detail refinement; 3) we propose a novel background line detection task into our auxiliary learning framework, to suppress interference of background lines or textures. In addition, we propose a high-quality matting benchmark, Plant-Mat, to evaluate matting methods on complex structures. Extensively quantitative and qualitative results show that our approach outperforms state-of-the-art mask-guided methods.

Free space detection is very important for vehicle navigation and safe driving. 3-D line segment reconstruction of a street is important for the free space detection because a street-view includes many line segments. For the free space detection, we propose a method for reconstructing 3-D line segments in a streetscape using a monocular in-vehicle camera. The 3-D reconstruction of the line segments is achieved by using each three images from an image sequence. Once accurate camera poses of these images are obtained, one of the remaining crucial problems is to match the line segments between the images correctly. A strategy for finding correspondence of the line segments is as follows: First, the correspondences of line segment candidates are searched by using a two-view constraint. However, the two-view constraint has difficulty on determining an unique correspondence geometrically. Therefore, the candidates of the line segment correspondences are reduced using a three-view constraint. In order to improve the accuracy, the proposed method exploits a color feature of the line segment and a preliminary knowledge of the vehicle motion. Finally, the line segments are reconstructed using the correspondences. From an experimental result, we confirmed the effectiveness of the proposed method. Application to the free space detection demonstrated the usefulness of the reconstructed line segments.

We propose a method to remove moving objects from an in-vehicle camera image sequence by fusing multiple image sequences. Driver assistance systems and services such as Google Street View require images containing no moving object. The proposed scheme consists of three parts: (i) collection of many image sequences along the same route by using vehicles equipped with an omni-directional camera, (ii) temporal and spatial registration of image sequences, and (iii) mosaicing partial images containing no moving object. Experimental results show that 97.3% of the moving object area could be removed by the proposed method.

We propose a distributed XML stream filtering system that uses a large number of subscribers' profiles, written in XPath expressions, to filter XML streams and then publish the filtered data in real-time. To realize the proposed system, we define XPath expression features on XML data and utilize them to forecast the servers' loads. Our method is realized by combining methods to share the total transfer loads of each filtering server and to equalize the sum of overlap size between filtering servers. Experiments show that the rate at which the publishing time increases with the number of XPath expressions is three times smaller in the proposed system than in the round-robin method. Furthermore, the overhead of the proposed method is quite low.