The atmospheric boundary layer is an important atmospheric feature that affects environmental health and weather forecasting. In this study, we proposed a graphics algorithm for the derivation of atmospheric boundary layer height (BLH) from the Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observations (CALIPSO) data. Owing to the differences in scattering intensity between molecular and aerosol particles, the total attenuated backscatter coefficient 532 and attenuated backscatter coefficient 1064 were used simultaneously for BLH detection. The proposed algorithm transformed the gradient solution into graphics distribution solution to overcome the effects of large noise and improve the horizontal resolution. This method was then tested with real signals under different horizontal smoothing numbers (1, 3, 15 and 30). The algorithm provided a reliable result when the horizontal smoothing number was greater than 5. Finally, the results of BLH obtained by CALIPSO data were compared with the results retrieved by the ground-based Lidar and radiosonde (RS) measurements. Under the horizontal smoothing number of 15, 9 and 3, the correlation coefficients between the BLH derived by the proposed algorithm and ground-based Lidar were 0.72, 0.72 and 0.14, respectively, and those between the BLH derived by the proposed algorithm and radiosonde measurements were 0.59, 0.59 and 0.07. When the horizontal smoothing number was 15 and 9, the CALIPSO BLH derived by the proposed method demonstrated a good correlation with ground-based Lidar and RS. This finding indicated that the proposed algorithm can be applied to the CALIPSO satellite data with 3 and 5 km horizontal resolution.