The paper presents an automatic region detection based method to reconstruct street scenes from driving recorder images. The driving recorder in this paper is a dashboard camera that collects images while the motor vehicle is moving. An enormous number of moving vehicles are included in the collected data because the typical recorders are often mounted in the front of moving vehicles and face the forward direction, which can make matching points on vehicles and guardrails unreliable. Believing that utilizing these image data can reduce street scene reconstruction and updating costs because of their low price, wide use, and extensive shooting coverage, we therefore proposed a new method, which is called the Mask automatic detecting method, to improve the structure results from the motion reconstruction. Note that we define vehicle and guardrail regions as “mask” in this paper since the features on them should be masked out to avoid poor matches. After removing the feature points in our new method, the camera poses and sparse 3D points that are reconstructed with the remaining matches. Our contrast experiments with the typical pipeline of structure from motion (SfM) reconstruction methods, such as Photosynth and VisualSFM, demonstrated that the Mask decreased the root-mean-square error (RMSE) of the pairwise matching results, which led to more accurate recovering results from the camera-relative poses. Removing features from the Mask also increased the accuracy of point clouds by nearly 30%–40% and corrected the problems of the typical methods on repeatedly reconstructing several buildings when there was only one target building.

Lakes and reservoirs are important parts of ecosystems and social developments. Separating scientific research on lakes and reservoirs is not conducive to measure water regulation services and defense against natural disasters. Accurate information for surface water is of great significance to the lake and reservoir management. To address this problem, we proposed a new automated lake and reservoir extraction process (LREP), which applied the modified two-mode (MTM) method to extract water from partial images by calculating thresholds in the normalized difference water index (NDWI) and the near-infrared (NIR) band; then, we estimated the segmentation thresholds from a set of NDWI thresholds obtained for the remaining images. Subsequently, a series of feature factors were used to remove rivers, shadows, mountains, and ponds. Finally, a new shape parameter called complexity was introduced to describe the edge characteristics of water bodies, distinguishing lakes and reservoirs from paddy fields and remaining ponds. We verified the algorithm using 154 Gaofen-2 images covering three cities: Liaoyuan, Xianning and Zigong. Results indicated that LREP performed well, with the overall accuracy of 99.38%, 99.27%, 98.72% and Kappa coefficients of 0.9195, 0.9649 and 0.9163 for Liaoyuan, Xianning, and Zigong, respectively. This method has the potential to monitor a variety of lakes and reservoirs, including lost lakes, new reservoirs and surface water quality.

Chlorophyll-a concentration is an important parameter of the Southern Ocean water environment, and is influenced by factors such as melting sea-ice and so on. This paper validated and justified the applicability of chlorophyll-a and sea-ice extent derived from MODIS data in understanding the spatial-temporal chlorophyll-a distribution in the Southern Ocean. The sea-ice cover reduced evenly between October and January, and the distribution of Chlorophyll-a varies with latitude and the distribution of melting sea-ice.