Button cell ingestion is a common household accident among infants, often leading to serious complications that require immediate diagnosis and urgent removal. We report five cases of button cell ingestion involving i...Button cell ingestion is a common household accident among infants, often leading to serious complications that require immediate diagnosis and urgent removal. We report five cases of button cell ingestion involving infants aged between 9 and 32 months, including four boys and one girl. The ingestion was accidentally discovered in two infants, while in the other three, it was suspected during play. In three cases, mothers attempted to induce vomiting by giving fluids, but the batteries remained in the digestive tract for 38 hours to 5 days. After confirming the diagnosis, the batteries were removed within 4 to 36 hours. The locations of the cells were the esophagus in two cases, the cardia in one, the stomach in one, and the bowel in one. One case involved a large cell in the esophagus, while the others involved smaller cells. Complications occurred in four cases, including esotracheal fistula, esophageal ulceration, and perforation of the jejunum and caecum. In one case, the digestive mucosa appeared normal upon endoscopy. One patient died.展开更多
Fast recognition of elevator buttons is a key step for service robots toride elevators automatically. Although there are some studies in this field, noneof them can achieve real-time application due to problems such a...Fast recognition of elevator buttons is a key step for service robots toride elevators automatically. Although there are some studies in this field, noneof them can achieve real-time application due to problems such as recognitionspeed and algorithm complexity. Elevator button recognition is a comprehensiveproblem. Not only does it need to detect the position of multiple buttonsat the same time, but also needs to accurately identify the characters on eachbutton. The latest version 5 of you only look once algorithm (YOLOv5) hasthe fastest reasoning speed and can be used for detecting multiple objects inreal-time. The advantages ofYOLOv5 make it an ideal choice for detecting theposition of multiple buttons in an elevator, but it’s not good at specific wordrecognition. Optical character recognition (OCR) is a well-known techniquefor character recognition. This paper innovatively improved the YOLOv5network, integrated OCR technology, and applied them to the elevator buttonrecognition process. First, we changed the detection scale in the YOLOv5network and only maintained the detection scales of 40 ∗ 40 and 80 ∗ 80, thusimproving the overall object detection speed. Then, we put a modified OCRbranch after the YOLOv5 network to identify the numbers on the buttons.Finally, we verified this method on different datasets and compared it withother typical methods. The results show that the average recall and precisionof this method are 81.2% and 92.4%. Compared with others, the accuracyof this method has reached a very high level, but the recognition speed hasreached 0.056 s, which is far higher than other methods.展开更多
文摘Button cell ingestion is a common household accident among infants, often leading to serious complications that require immediate diagnosis and urgent removal. We report five cases of button cell ingestion involving infants aged between 9 and 32 months, including four boys and one girl. The ingestion was accidentally discovered in two infants, while in the other three, it was suspected during play. In three cases, mothers attempted to induce vomiting by giving fluids, but the batteries remained in the digestive tract for 38 hours to 5 days. After confirming the diagnosis, the batteries were removed within 4 to 36 hours. The locations of the cells were the esophagus in two cases, the cardia in one, the stomach in one, and the bowel in one. One case involved a large cell in the esophagus, while the others involved smaller cells. Complications occurred in four cases, including esotracheal fistula, esophageal ulceration, and perforation of the jejunum and caecum. In one case, the digestive mucosa appeared normal upon endoscopy. One patient died.
基金the Research and Implementation of An Intelligent Driving Assistance System Based on Augmented Reality in Hebei Science and Technology Support Plan (Grant Number 17210803D)Science and Technology Research Project of Higher Education in Hebei Province (Grant Number ZD2020318)Middle School Students Science and Technology Innovation Ability Cultivation Special Project (Grant No.22E50075D)and project (Grant No.1181480).
文摘Fast recognition of elevator buttons is a key step for service robots toride elevators automatically. Although there are some studies in this field, noneof them can achieve real-time application due to problems such as recognitionspeed and algorithm complexity. Elevator button recognition is a comprehensiveproblem. Not only does it need to detect the position of multiple buttonsat the same time, but also needs to accurately identify the characters on eachbutton. The latest version 5 of you only look once algorithm (YOLOv5) hasthe fastest reasoning speed and can be used for detecting multiple objects inreal-time. The advantages ofYOLOv5 make it an ideal choice for detecting theposition of multiple buttons in an elevator, but it’s not good at specific wordrecognition. Optical character recognition (OCR) is a well-known techniquefor character recognition. This paper innovatively improved the YOLOv5network, integrated OCR technology, and applied them to the elevator buttonrecognition process. First, we changed the detection scale in the YOLOv5network and only maintained the detection scales of 40 ∗ 40 and 80 ∗ 80, thusimproving the overall object detection speed. Then, we put a modified OCRbranch after the YOLOv5 network to identify the numbers on the buttons.Finally, we verified this method on different datasets and compared it withother typical methods. The results show that the average recall and precisionof this method are 81.2% and 92.4%. Compared with others, the accuracyof this method has reached a very high level, but the recognition speed hasreached 0.056 s, which is far higher than other methods.
