Mainstream lane marker detection methods are implemented by predicting the overall structure and deriving parametric curves through post-processing. Complex lane line shapes require high-dimensional output of CNNs to model global structures, which further increases the demand for model capacity and training data. In contrast, the locality of a lane marker has finite geometric variations and spatial coverage. We propose a novel lane marker detection solution, FOLOLane, that focuses on modeling local patterns and achieving prediction of global structures in a bottom-up manner. Specifically, the CNN models lowcomplexity local patterns with two separate heads, the first one predicts the existence of key points, and the second refines the location of key points in the local range and correlates key points of the same lane line. The locality of the task is consistent with the limited FOV of the feature in CNN, which in turn leads to more stable training and better generalization. In addition, an efficiency-oriented decoding algorithm was proposed as well as a greedy one, which achieving 36% runtime gains at the cost of negligible performance degradation. Both of the two decoders integrated local information into the global geometry of lane markers. In the absence of a complex network architecture design, the proposed method greatly outperforms all existing methods on public datasets while achieving the best state-of-the-art results and real-time processing simultaneously.

No abstract

No abstract

Image-based water level measurement is a visual-sensing technique which automatically inspects the reading of the water line via image processing instead of the human eye. It can be realized easily on an existing video surveillance system and has advantages like low cost, non-contact, as well as results that are verifiable. It has the potential to be widely used in flood and waterlogging monitoring, while facing the challenge that water-line detection under complex natural or artificial illumination conditions is quite difficult in field applications. To handle this problem, a method is proposed assuming that the water line is generally located on the row with the largest local change of gray or edge features in the image of the water gauge. The water line is determined by coarse-to-fine detection of the position of the maximum mean difference (MMD) of the horizontal projections of gray and edge images. Image-based flow-level measurement systems were developed at two measurement sites. In situ comparative experiments were conducted with the float-type stage gauge and other image-based methods. The results show that the fusion of gray and edge features can overcome the shortcomings of single feature methods under complex illumination conditions such as dim light, glares, shadows and artificial night lighting. A coarse-to-fine strategy utilizes the periodicity of the surface pattern distribution of the standard bicolor water gauge, which improves the reliability of water-line detection. The resolution and accuracy of water-level measurement are 1 mm and 1 cm, respectively. In particular, the MMD value is efficient at identifying extremely unfavorable conditions and reducing gross errors.

No abstract