Structured Edge Detection Research Articles

Automatic identification of smoking behaviour in public places based on improved YOLO algorithm

This paper proposes an automatic identification method of smoking behaviour in public places based on the improved You Only Look Once (YOLO) algorithm. The histogram of oriented gradient (HOG) feature method is used to detect the face part of smokers, taking the detected face image as the input, the edge of the image is extracted by using the structured edge detection operator of the edge box. The gesture dataset is re-clustered by K-means++ clustering algorithm to obtain a priori frame that is more suitable for gesture recognition; and in the traditional YOLO network, the SPP spatial pyramid pooling module is added to realise the fusion of local gesture features and global gesture features, to complete the automatic identification of smoking behaviour in public places. The results show that the highest recognition rate of this method is 94.3%, the accuracy and recall rate are higher than those of the traditional methods, and the recognition results are more comprehensive.

Geological model and development of the Cenozoic Wiang Pa Pao Basin, Chiang Rai Province, Northern Thailand, based on gravity data modelling and surface structural interpretation

3-D Inverse gravity modelling, constrained by surface geological data across the Neogene Wiang Pa Pao Basin (WPB), Northern Thailand, provides new subsurface models of the basin geometry and its structural development. The intermontaine WPB is seismically active and exhibits many geothermal sites; both are indicative of active fault zones. Six hundred thirty-six terrestrial gravity stations with ~500 m spacing were acquired. The residual Complete Bouguer Anomaly map (CBA) reveals an N–S elongate basin characterized by gravity lows bounded by gravity highs on the eastern margin of the basin (metasedimentary basement), and moderate gravity anomalies on the western margin (granitic basement). Structural edge detection revealed N–S trending faults along the eastern and western margins linked by NE–SW and NW–SE trending lineaments. The 3-D gravity model indicates an asymmetric graben; with a maximum depocenter depth of ~1300 m. Surface structure and seismicity confirm the gravity interpretation that the WPB is a dextral transtensional basin characterized by WSW–ENE trending R'-shears and NNE–SSW R-shears distributed in duplex-like geometries along the N–S trending principal displacement zone. The WPB displays unusually well-developed R’-shears, where Palaeozoic metasedimentary rocks in the basement and Cenozoic basin sediments are present, these faults disappear to the south, where the main N–S fault resides entirely within the granite. The WPB is associated with Cenozoic multi-phase rifting: in the Late Oligocene–Miocene, major rift basins formed under W–E extension, strongly influenced by WSW–ENE to NE–SW and NW–SE pre-existing trends. In the Latest Miocene–Recent, the younger basins, including the WPB, underwent dextral strike-slip along new and existing N–S dextral fault trends.

SeNet: Structured Edge Network for Sea–Land Segmentation

Separating an optical remote sensing image into sea and land areas is very challenging yet of great importance to coastline extraction and subsequent object detection. Traditional methods based on handcrafted feature extraction and image processing often face this dilemma when confronting high-resolution remote sensing images for their complicated texture and intensity distribution. In this letter, we apply the prevalent deep convolutional neural networks to the sea-land segmentation problem and make two innovations on top of the traditional structure. First, we propose a local smooth regularization to achieve better spatially consistent results, which frees us from the complicated morphological operations that are commonly used in traditional methods. Second, we use a multitask loss to simultaneously obtain the segmentation and edge detection results. The attached structured edge detection branch can further refine the segmentation result and dramatically improve edge accuracy. Experiments on a set of natural-colored images from Google Earth demonstrate the effectiveness of our approach in terms of quantitative and visual performances compared with state-of-the-art methods.

Structural sparse representation-based semi-supervised learning and edge detection proposal for visual tracking

In discriminative tracking, lots of tracking methods easily suffer from changes of pose, illumination and occlusion. To deal with this problem, we propose a novel object tracking method using structural sparse representation-based semi-supervised learning and edge detection. First, the object appearance model is constructed by extracting sparse code features on different layers to exploit local information and holistic information. To utilize unlabelled samples information, the semi-supervised learning is introduced and a classifier is trained which is used to measure candidates. In addition, an auxiliary positive sample set is maintained to improve the performance of the classifier. We subsequently adopt an edge detection to alleviate the error accumulation based on the ranking results from the learned classifier. Finally, the proposed method is implemented under the Bayesian inference framework. Both the proposed tracker and several current trackers are tested on some challenging videos, where the target objects undergo pose change, illumination and occlusion. The experimental results demonstrate that the proposed tracker outperforms the other state-of-the-art methods in terms of effectiveness and robustness.

Structural Edge Detection Method from 3D Point Cloud and Its Capability

Structural Edge Detection Method from 3D Point Cloud and Its Capability