With the development of computer vision technology, it is possible to inspect the inst ruments regularly through the inspection robot in some complex industrial environm ents. However, the realization of the inspection depends on the precise localization of instruments . Here, a method based on locally adaptive regression kernels (LARK) is introduced to achieve quick localiza tion of instruments. LARK can quickly search the visual object without training or too much preprocessing, which greatly improve the efficiency of the instruments localization. Firstly, the salient features are extracted and analogous objects are searched and with the target image to find al l possible similar matches. Then nonmaxima suppression is employed to localize th e target object. The instruments images with different scaling taken from different angles are used in experiments. Experimental results suggest that the a lgorithm is accurate and can meet the requirements of instrument localiza tion in industrial environments.