This paper addresses the problem of target detection in dynamic environments. A key challenge here is to simultaneously achieve high probabilities of correct detection with low false alarm rates under limited computation and communication resources. To this end, a procedure of binary hypothesis testing is proposed based on agglomerative hierarchical feature clustering. The proposed procedure has been experimentally validated in the laboratory setting on a mobile robot for target detection by using multiple homogeneous (with different orientations) infrared sensors in the presence of changing ambient light intensities. The experimental results show that the proposed target detection procedure with feature-level sensor fusion outperforms those with decision-level sensor fusion.