Dealing with compressed video streams in mobile robotics is an unavoidable fact of life. Transferring images between mobile robots or to the Cloud using wireless links can practically only be achieved using lossy video compression. This introduces artifacts that often make image processing challenging. Recent algorithms based on deep neural networks, as advanced as they are, are commonly trained and evaluated on datasets of high-fidelity images which are typically not captured from aerial views. In this work we evaluate a number of deep neural network based object detection algorithms in the context of aerial search and rescue scenarios where real-time and robust detection of human bodies is a priority. We provide an evaluation using a number of video sequences collected in-flight using Unmanned Aerial Vehicle (UAV) platforms in different environmental conditions. We also describe the detection performance degradation under limited bitrate compression using H.264, H.265 and VP9 video codecs, in addition to analyzing the timing effects of moving image processing tasks to off-board entities.