Multiple-Object Tracking Using Histogram Stamp Extraction in CCTV Environments

Object tracking,an important technology in the field of image processing and computer vision,is used to continuously track a specific object or person in an image.This technology may be effective in identifying the same person within one image,but it has limitations in handling multiple images owing to the difficulty in identifying whether the object appearing in other images is the same.When tracking the same object using two or more images,there must be a way to determine that objects existing in different images are the same object.Therefore,this paper attempts to determine the same object present in different images using color information among the unique information of the object.Thus,this study proposes a multiple-object-tracking method using histogram stamp extraction in closed-circuit television applications.The proposed method determines the presence or absence of a target object in an image by comparing the similarity between the image containing the target object and other images.To this end,a unique color value of the target object is extracted based on its color distribution in the image using three methods:mean,mode,and interquartile range.The Top-N accuracy method is used to analyze the accuracy of each method,and the results show that the mean method had an accuracy of 93.5%(Top-2).Furthermore,the positive prediction value experimental results show that the accuracy of the mean method was 65.7%.As a result of the analysis,it is possible to detect and track the same object present in different images using the unique color of the object.Through the results,it is possible to track the same object that can minimize manpower without using personal information when detecting objects in different images.In the last response speed experiment,it was shown that when the mean was used,the color extraction of the object was possible in real time with 0.016954 s.Through this,it is possible to detect and track the same object in real time when using the proposed method.

Stratified computed tomography findings improve diagnostic accuracy for appendicitis

AIM:To improve the diagnostic accuracy in patients with symptoms and signs of appendicitis,but without confirmative computed tomography(CT) findings. METHODS:We retrospectively reviewed the database of 224 patients who had been operated on for the suspicion of appendicitis,but whose CT findings were negative or equivocal for appendicitis. The patient population was divided into two groups:a pathologically proven appendicitis group(n = 177) and a nonappendicitis group(n = 47). The CT images of these patients were re-evaluated according to the characteristic CT features as described in the literature. The re-evaluations and baseline characteristics of the two groups were compared.RESULTS:The two groups showed significant differences with respect to appendiceal diameter,and the presence of periappendiceal fat stranding and intraluminal air in the appendix.A larger proportion of patients in the appendicitis group showed distended appendices larger than 6.0 mm(66.3%vs 37.0%;P<0.001),periappendiceal fat stranding(34.1%vs 8.9%;P=0.001),and the absence of intraluminal air(67.6%vs 48.9%;P=0.024)compared to the non-appendicitis group.Furthermore,the presence of two or more of these factors increased the odds ratio to 6.8 times higher than baseline(95%CI:3.013-15.454;P<0.001).CONCLUSION:Appendiceal diameter and wall thickening,fat stranding,and absence of intraluminal air can be used to increased diagnostic accuracy for appendicitis with equivocal CT findings.

Determination of surgical priorities in appendicitis based on the probability of undetected appendiceal perforation

AIM:To identify risk factors of actual appendiceal perforation when computed tomography(CT)scans suggest nonperforated appendicitis and accordingly determine surgical priority.METHODS:We collected database of 1362 patients who underwent an appendectomy for acute appendicitis between 2006 and 2013.A single radiologist selected1236 patients whose CT scans were suggestive ofnonperforated appendicitis.Patients were divided into 2 groups:actual nonperforation group and actual perforation group according to intraoperative and pathologic features.Comparison of the 2 groups were made using binary logistic regression.RESULTS:Of 1236 patients,90(7.3%)were found to have actual appendiceal perforation.Four risk factors related with actual appendiceal perforation were identified:body temperature≥37.6℃(HR=1.912,95%CI:1.161-3.149;P=0.011),out-ofhospital symptom duration≥72 h(HR=2.454,95%CI:1.292-4.662;P=0.006),age≥35 years(HR=3.358,95%CI:1.968-5.728;P<0.001),and appendiceal diameter on CT scan≥8 mm(HR=4.294,95%CI:1.034-17.832;P=0.045).Actual appendiceal perforation group showed longer operation time,later initiation of diet,longer use of parenteral narcotics,longer hospital stay,and higher incidence of postoperative complications(P<0.05).CONCLUSION:We proposed here new criteria to select patients with adverse clinical outcomes after appendectomy among the patients with radiologically nonperforated appendicitis.Surgical appendectomy outcomes could be improved by determining the surgical priority according to our criteria.