Steve Matsumoto

  • Citations Per Year
Learn More
The impressive advances in robotic spatial reasoning over the past decade have relied primarily on rich sensory data provided by laser range finders. Relative to cameras, however, lasers are heavy, bulky, power-hungry, and expensive. This work proposes and evaluates an image-segmentation pipeline that produces range scans from ordinary webcameras. Starting(More)
In the Android operating system, each application consists of a set of components that communicate with each other via messages called Intents. The current implementation of Intent handling is such that developers can inadvertently write insecure code that allows malicious applications to intercept or inject Intents to steal sensitive information or induce(More)
This work presents and evaluates the PixelLaser system, designed to estimate range-to-obstacle scans from single images. Its visual pipeline uses nearest-neighbor texture-matching to segment groundplane (traversable) texture from non-groundplane (obstacle) texture. Using the known pose of a webcamera, the system then transforms these segmentations into(More)
The problem of finding a robot's range-to-obstacles is a fundamental one with an elegant solution: the laser range finder (LRF). This work has developed algorithms for replacing a laser with a camera for indoor applications. Our approach uses machine learning algorithms to segment the groundplane from single images flexibly, quickly, and robustly. We then(More)
  • 1