At present, most of the existing target detection algorithms use the method of region proposal to search for the target in the image. The most effective regional proposal method usually requires thousands of target prediction areas to achieve high recall rate.This lowers the detection efficiency. Even though recent region proposal network approach have yielded good results by using hundreds of proposals, it still faces the challenge when applied to small objects and precise locations. This is mainly because these approaches use coarse feature. Therefore, we propose a new method for extracting more efficient global features and multi-scale features to provide target detection performance. Given that feature maps under continuous convolution lose the resolution required to detect small objects when obtaining deeper semantic information; hence, we use rolling convolution (RC) to maintain the high resolution of low-level feature maps to explore objects in greater detail, even if there is no structure dedicated to combining the features of multiple convolutional layers. Furthermore, we use a recurrent neural network of multiple gated recurrent units (GRUs) at the top of the convolutional layer to highlight useful global context locations for assisting in the detection of objects. Through experiments in the benchmark data set, our proposed method achieved 78.2% mAP in PASCAL VOC 2007 and 72.3% mAP in PASCAL VOC 2012 dataset. It has been verified through many experiments that this method has reached a more advanced level of detection.
The paper discusses the results of investigations of material, tribological and anti-corrosion properties of hybrid coatings of the Cr/CrN type, consisting of chromium and chromium nitride, formed on the surface of alloy tool steel by the Arc-PVD method. Investigations of the morphology and microstructure of hybrid coatings, as well as of their phase composition were carried out. The studies on mechanical properties included tests on hardness and Young’s modulus using the nanoindentation method. Tests on adhesion were conducted using the scratch-test method. Tribological properties of the obtained coatings were evaluated by the pin-on-disc method. Resistance to corrosion was determined by electrochemical methods. It was shown that hybrid coatings of the Cr/CrN type are characterized by good adhesion to the substrate and very good tribological properties, as well as by very good resistance to corrosion in a solution containing chlorine ions.