Learn More
We are developing a cooking navigation system, which helps even a novice user to cook several recipes in parallel without failure, while improving an advanced user's skill further. To realize this, the system optimizes the cooking procedure considering the following restrictions: (1) Duration of cooking, (2) Accuracy of cooking, and (3) Learning effect, by(More)
We propose a method to create process flow graphs automatically from textbooks for cooking programs. This is realized by understanding context by narrowing down the domain to cooking, and making use of domain specific constraints and knowledge. Since it is relatively easy to extract significant keywords from cooking procedures, we create a domain specific(More)
We propose a weather recognition method from in-vehicle camera images that uses a subspace method to judge rainy weather by detecting raindrops on the windshield. "Eigendrops" represent the principal components extracted from raindrop images in the learning stage. Then the method detects raindrops by template matching. In experiments using actual video(More)
We propose a novel object detection and tracking method in order to detect and track objects necessary to describe contents of a soccer game. On the contrary to intensity oriented conventional object detection methods, the proposed method refers to color rarity and local edge property, and integrally evaluate them by a fuzzy function to achieve better(More)
In this paper, we propose a method for recognition of road markings from in-vehicle camera images. A road marking in in-vehicle camera images has a variety of appearance due to the change of position and distance between the camera and the road marking, blur effect, and so on. Therefore, accurate recognition of road markings becomes difficult in real(More)
We propose a topic-based inter-video news video corpus structuring method and a visual interface to efficiently browse through the structured corpus. Such inter-video structuring was not deeply sought in previous works. The topic-based structure is analyzed by closed-caption text analysis; topic segmentation and tracking. The visual interface provides the(More)
Obtaining an accurate vehicle position is important for intelligent vehicles in supporting driver safety and comfort. This paper proposes an accurate ego-localization method by matching in-vehicle camera images to an aerial image. There are two major problems in performing an accurate matching: (1) image difference between the aerial image and the(More)
Using appropriate training data is necessary to robustly recognize low-resolution characters by the subspace method. Former learning methods used characters actually captured by a camera, which required the collection of characters of all categories in various conditions. In this paper, we propose a new learning method that generates training data by a(More)
In this paper, we propose the concept of synthesizing a multimedia cooking recipe from a text recipe and a database composed of video clips depicting cooking operations. A multimedia cooking recipe is a cooking recipe where each cooking operation is associated with a corresponding video clip depicting it, aimed to facilitate the understanding of cooking(More)