In some security applications, it is important to transmit just enough information to take the right decisions. Traditional video codecs try to maximize the global quality, irrespective of the video content pertinence for certain tasks. To better maintain the semantics of the scene, some approaches allocate more bitrate to the salient information. In this paper, a semantic video compression scheme based on seam carving is proposed. The idea is to suppress non-salient parts of the video by seam carving. The reduced sequence is encoded with H.264/AVC while the seams are encoded with our approach. The main contributions of this paper are (1) an algorithm that segments the sequence into group of pictures, depending on the content, (2) a spatio-temporal seam clustering method, (3) an isolated seam discarding technique, improving the seam encoding, (4) a new seam modeling, avoiding geometric distortion and resulting in a better control of the seam shapes, and (5) a new encoder which reduces the overall bit-rate. A full reference object-oriented quality metric is used to assess the performance of the approach. Our approach outperforms traditional H.264/AVC intra encoding with a Bjontegaard's rate improvement between 7.02 and 21.77% while maintaining the quality of the salient objects.