Despite their increasing sophistication, wireless sensor networks still do not exploit the most powerful of the human senses: vision. Indeed, vision provides humans with unmatched capabilities to distinguish objects and identify their importance. This work seeks to provide wireless sensor networks with similar capabilities by exploiting emerging, cheap, low-power and small form factor CMOS imaging technology. In fact, we go beyond the stereo capabilities of human vision, and exploit the large scale of sensor networks to provide multiple, widely different perspectives of physical phenomena. We have developed a small camera device called Cyclops that bridges the gap between the computationally constrained wireless sensor nodes such as Motes, and CMOS imagers which, while low power and inexpensive, are nevertheless designed to mate with resource-rich hosts. Cyclops enables development of new class of vision applications that span across wireless sensor network.