For online prediction in live streaming applications, selecting low-complexity features is critical to ensure low-latency video streaming without disruptions. For each frame/ video/ video segment, the complexity features, i.e., the average texture energy, the average gradient of the texture energy, and the average brightness are determined. Similarly, the brightness and texture energy features are analyzed for chroma channels. A DCT-based energy function is introduced to determine the block-wise texture of each frame. The spatial and temporal features of the video/ video segment are derived from the DCT-based energy function. The Video Complexity Analyzer (VCA) project is launched in 2022, aiming to provide the most efficient, highest performance spatial and temporal complexity prediction of each frame/ video/ video segment which can be used for a variety of applications like shot/scene detection, online per-title encoding.