No abstract

Computer‐vision and deep‐learning techniques are being increasingly applied to inspect, monitor, and assess infrastructure conditions including detection of cracks. Traditional vision‐based methods to detect cracks lack accuracy and generalization to work on complicated infrastructural conditions. This paper presents a novel context‐aware deep convolutional semantic segmentation network to effectively detect cracks in structural infrastructure under various conditions. The proposed method applies a pixel‐wise deep semantic segmentation network to segment the cracks on images with arbitrary sizes without retraining the prediction network. Meanwhile, a context‐aware fusion algorithm that leverages local cross‐state and cross‐space constraints is proposed to fuse the predictions of image patches. This method is evaluated on three datasets: CrackForest Dataset (CFD) and Tomorrows Road Infrastructure Monitoring, Management Dataset (TRIMMD) and a Customized Field Test Dataset (CFTD) and achieves Boundary F1 (BF) score of 0.8234, 0.8252, and 0.7937 under 2‐pixel error tolerance margin in CFD, TRIMMD, and CFTD, respectively. The proposed method advances the state‐of‐the‐art performance of BF score by approximately 2.71% in CFD, 1.47% in TRIMMD, and 4.14% in CFTD. Moreover, the averaged processing time of the proposed system is 0.7 s on a typical desktop with Intel® Quad‐Core™ i7‐7700 CPU@3.6 GHz Processor, 16GB RAM and NVIDIA GeForce GTX 1060 6GB GPU for an image of size 256 × 256 pixels.

No abstract

No abstract

Understanding prehistoric projectile weaponry performance is fundamental to unraveling past humans' survival and the evolution of technology. one important debate involves how deeply stone-tipped projectiles penetrate a target. theoretically, all things being equal, projectiles with smaller tip cross-sectional geometries should penetrate deeper into a target than projectiles with larger tip cross-sectional geometries. Yet, previous experiments have both supported and questioned this theoretical premise. Here, under controlled conditions, we experimentally examine fourteen types of stone-tipped projectile each possessing a different cross-sectional geometry. Our results show that both tip cross-sectional area (tcSA) and tip cross-sectional perimeter (tcSp) exhibit a strong, significant inverse relationship with target penetration depth, although TCSP's relationship is stronger. We discuss why our experimental results support what is mathematically predicted while previous experiments have not. our results are consistent with the hypothesis that when stone tip cross-sectional geometries become smaller over time in particular contexts, this evolution may be due to the selection of these attributes for increased penetration.