An Efficient Squirrel Search Algorithm based Vector Quantization for Image Compression in Unmanned Aerial Vehicles

Unmanned aerial vehicles (UAVs) typically fly at low altitudes for capturing high-resolution images covering smaller areas. Since short flights also and high-resolution cameras lead to the generation of massive gigabytes (GBs) of data regions, image compression is essential to compress the data to a compact form resulted in shorter file size without any loss of quality. The vector quantization (VQ) is an effective type of image compression and the conventionally employed technique namely Linde-Buzo-Gray (LBG) algorithm continually created local optimal codebook. The codebook design process can be considered as a high dimensional optimization problem and can be resolved by the use of swarm intelligence algorithms. This paper designs a novel squirrel search algorithm (SSA) with LBG based image compression technique, called SSA-LBG for UAVs. The SSA is applied for the construction of codebooks for VQ and it makes use of LBG model as the initialization of the SSA for VQ. The application of SSA-LBG results in effective compression with low computation time (CT) and high peak signal to noise ratio (PSNR). An extensive set of simulations were performed on benchmark test images and the results are examined with respect to CT and PSNR undervarying bit rates and codebook sizes.