We present a real-time approach for circular and polygonal road signs detection1 in still images, regardless of their pose and orientation. Object detection is done using a pairwise gradient-based symmetry transform able to detect circles and polygons indistinctly. This symmetry transform of gradient orientation, the so-called Bilateral Chinese Transform BCT, decomposes an object into a set of parallel contours with opposite gradients, and models this gradient field symmetry using an accumulation of radial symmetry evidences. On a test database of 89 images 640x480 containing 92 road signs, 79 are correctly detected (86%) with 25 false positives using the BCT approach in about 30 ms/image.