Sliding window approaches have been widely used for object recognition tasks in recent years. They guarantee an investigation of the entire input image for the object to be detected and allow a localization of that object. Despite the current trend towards deep neural networks, sliding window methods are still used in combination with convolutional neural networks. The risk of overlooking an object is clearly reduced compared to alternative detection approaches which detect objects based on shape, edges or color. Nevertheless, the sliding window technique strongly increases the computational effort as the classifier has to verify a large number of object candidates. This paper proposes a sliding window approach which also uses depth information from a stereo camera. This leads to a greatly decreased number of object candidates without significantly reducing the detection accuracy. A theoretical investigation of the conventional sliding window approach is presented first. Other publications to date only mentioned rough estimations of the computational cost. A mathematical derivation clarifies the number of object candidates with respect to parameters such as image and object size. Subsequently, the proposed disparity sliding window approach is presented in detail. The approach is evaluated on pedestrian detection with annotations and images from the KITTI object detection benchmark. Furthermore, a comparison with two state-of-the-art methods is made. Code is available in C++ and Python https://github.com/julimueller/ disparity-sliding-window.
VKORC1 has been identified some years ago as the gene encoding vitamin K epoxide reductase (VKOR) - the target protein for coumarin derivates like warfarin or phenprocoumon. Resistance against warfarin and other coumarin-type anticoagulants has been frequently reported over the last 50 years in rodents due to problems in pest control as well as in thrombophilic patients showing variable response to anticoagulant treatment. Many different mutations have already been detected in the VKORC1 gene leading to warfarin resistance in rats, mice and in humans. Since the conventional in vitro dithiothreitol (DTT)-driven VKOR enzymatic assay often did not reflect the in vivo status concerning warfarin resistance, we recently developed a cell culture-based method for coexpression of VKORC1 with coagulation factor IX and subsequent measurement of secreted FIX in order to test warfarin inhibition in wild-type and mutated VKORC1.In the present study, we coexpressed wild-type factor IX with 12 different VKORC1 variants which were previously detected in warfarin resistant rats and mice. The results show that amino acid substitutions in VKORC1 maintain VKOR activity and are associated with warfarin resistance. When we projected in silico the amino acid substitutions onto the published three-dimensional model of the bacterial VKOR enzyme, the predicted effects matched well the catalytic mechanism proposed for the bacterial enzyme.The established cell-based system for coexpression of VKORC1 and factor IX uses FIX activity as an indicator of carboxylation efficiency. This system reflects the warfarin resistance status of VKORC1 mutations from anticoagulant resistant rodents more closely than the traditional DTT-driven enzyme assay. All mutations studied were also predicted to be involved in the reaction mechanism.
Summary Hereditary combined deficiency of the vitamin K‐dependent coagulation factors II, VII, IX, X, protein C, S and protein Z (VKCFD) is a very rare autosomal recessive inherited bleeding disorder. The phenotype may result from functional deficiency of either the γ ‐glutamyl carboxylase (GGCX) or the vitamin K epoxide reductase (VKOR) complex. We report on the third case of VKCFD1 with mutations in the γ ‐glutamyl carboxylase gene, which is remarkable because of compound heterozygosity. Two mutations were identified: a splice site mutation of exon 3 and a point mutation in exon 11, resulting in the replacement of arginine 485 by proline. Screening of 100 unrelated normal chromosomes by restriction fragment length polymorphism and denaturing high‐performance liquid chromatography analysis excluded either mutation as a frequent polymorphism. Substitution of vitamin K could only partially normalize the levels of coagulation factors. It is suggested that the missense mutation affects either the propeptide binding site or the vitamin K binding site of GGCX.
