Abhijit Ogale

Google Street View: Capturing the World at Street Level

Street View serves millions of Google users daily with panoramic imagery captured in hundreds of cities in 20 countries across four continents. A team of Google researchers describes the technical challenges involved in capturing, processing, and serving street-level imagery on a global scale.

Real-Time Pedestrian Detection With Deep Network Cascades

We present a new real-time approach to object detection that exploits the efficiency of cascade classifiers with the accuracy of deep neural networks. Deep networks have been shown to excel at classification tasks, and their ability to operate on raw pixel input without the need to design special features is very appealing. However, deep nets are notoriously slow at inference time. In this paper, we propose an approach that cascades deep nets and fast features, that is both very fast and very accurate. We apply it to the challenging task of pedestrian detection. Our algorithm runs in real-time at 15 frames per second. The resulting approach achieves a 26.2% average miss rate on the Caltech Pedestrian detection benchmark, which is competitive with the very best reported results. It is the first work we are aware of that achieves very high accuracy while running in real-time.

The Language of Action: A New Tool for Human-Centric Interfaces

Publisher Summary This chapter puts forward an argument that human activity can be expressed in a language, a special language with its own phonemes, its own morphemes (words), and its own syntax. This language can be inferred using machine learning techniques applied to gargantuan amounts of data collected by cameras or other sensor networks. Developing sensory-motor language creates bridges among several disciplines. It also provides a hierarchical structure that can lead to a successful industry. This chapter points to a research program and the application of its early realizations to a few domains. User interface designers today focus on nontraditional interfaces that make use of each of the five human senses. One of the major goals of human-centric interfaces is for humans to interact with robots or other machines as they do with other humans. Human-centric interfaces not only promise to dominate future in many applications, but might also begin a new phase in artificial intelligence by studying meaning through the utilization of both sensorimotor and symbolic representations, using machine learning techniques on the gargantuan amounts of data collected.

The Language of Action

Publisher Summary This chapter puts forward an argument that human activity can be expressed in a language, a special language with its own phonemes, its own morphemes (words), and its own syntax. This language can be inferred using machine learning techniques applied to gargantuan amounts of data collected by cameras or other sensor networks. Developing sensory-motor language creates bridges among several disciplines. It also provides a hierarchical structure that can lead to a successful industry. This chapter points to a research program and the application of its early realizations to a few domains. User interface designers today focus on nontraditional interfaces that make use of each of the five human senses. One of the major goals of human-centric interfaces is for humans to interact with robots or other machines as they do with other humans. Human-centric interfaces not only promise to dominate future in many applications, but might also begin a new phase in artificial intelligence by studying meaning through the utilization of both sensorimotor and symbolic representations, using machine learning techniques on the gargantuan amounts of data collected.