… In this paper we present an automatic cognition system, based on computer vision algorithms
and deep convolutional neural networks, designed to assist the visually impaired (VI) …

This paper presents a computer vision based sensory substitution device for the visually
impaired. Its main objective is to provide the users with a 3D representation of the environment …

This chapter focuses on computer vision techniques to assist visually impaired people to
navigate in an indoor environment. First, the problem is defined in terms of tasks, sensors, …

This chapter focuses on computer vision techniques to assist visually impaired people to
navigate in an indoor environment. First, the problem is defined in terms of tasks, sensors, …

… Compared to the tracking model, which was also trained without semantic labels, our
network learns more high-level object detectors. It also has more detectors for objects that make …

… This visuocentric focus is not without merit given the visual … making such a trip completely
without vision is incredibly daunting (… Performing such tasks without vision is incredibly scary to …

… sight demonstrate the fundamental principles contained in Dr. Bates' book, "Perfect Sight
Without … glasses discarded, it is possible to improve the vision without personally consulting a …

… Another class of algorithms used in the identified publications counted on direct computer
vision approaches without an adaptive machine learning component. For example, Garcia and …

… without direct line-ofsight [1, 3, 4, 13, 17, 19, 20, 27, 28, 39]. The ability to carry out recognition
without line-of-sight has … to perform recognition without direct line-of-sight by exploiting the …

… an object exists, even when no object is in sight. One big advantage of the context and object
de… For evaluation, we define an out of context face as a face without a visible body. Figure 9 …