In photogrammetry and object recognition

it's necessary to introduce the sensor planning strategies to improve the measurement accuracy. Sensor planning is a new research area in computer vision. Planning the parameters of camera and illumination purposefully can make task be performed effectively. In this paper some affecting factors which are essential to sensor planning are analyzed firstly. They are the parameters of camera and illumination

constrain of feature detectability

the models of sensor and object. After some specific sensor planning systems were summarized

the sensor planning systems are classified based on the methods they used

the goals

the number of sensors and a prior information. Then the problem of sensor planning is concluded to the optimization process which can be done in high dimensional space composed of the parameters of camera

lens

illumination and object models. Finally we show some possible developing directions

namely single camera system in active machine vision

multi camera network design solution

new optimization and combinatorial search method

rebuilding the uncertainty of characters and multi sensor data fusion.