Modern smartphone cameras capture high-resolution images, containing millions of pixels. However, computer vision tasks operate effectively on images of much lower resolution. The research team seeks to implement an adaptive sampling block within the imaging pipeline on an FPGA. The adaptive sampling block can utilize key information from the prior image to remove unimportant pixels from the next, as they are read-in from the sensor. The early removal of these pixels will reduce the energy spent operating on high-resolution images, while allowing for retained accuracy in computer vision tasks.