Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

29210results about How to "Accurate detection" patented technology

Safety indicator and method

A safety indicator monitors environment conditions detrimental to humans e.g., hazardous gases, air pollutants, low oxygen, radiation levels of EMF or RF and microwave, temperature, humidity and air pressure retaining a three month history to upload to a PC via infra red data interface or phone link. Contaminants are analyzed and compared to stored profiles to determine its classification and notify user of an adversity by stored voice messages from, via alarm tones and associated flashing LED, via vibrator for silent operation or via LCD. Environmental radiation sources are monitored and auto-scaled. Instantaneous radiation exposure level and exposure duration data are stored for later readout as a detector and dosimeter. Scans for EMF allow detection with auto scaling of radiation levels and exposure durations are stored for subsequent readout. Electronic bugs can be found with a high sensitivity EMF range setting. Ambient temperature measurements or humidity and barometric pressure can be made over time to predict weather changes. A PCS RF link provides wireless remote communications in a first responder military use by upload of alarm conditions, field measurements and with download of command instructions. The link supports reception of telemetry data for real time remote monitoring of personnel via the wrist band for blood pressure, temperature, pulse rate and blood oxygen levels are transmitted. Commercial uses include remote environmental data collection and employee assignment tasking. GPS locates personnel and reporting coordinates associated with alarm occurrences and associated environmental measurements.
Owner:NTCG

Bed exit and patient detection system

A bed exit and patient detection system especially adapted for use in the general medical or surgical floor area of a hospital or other healthcare facility as part of a vital signs monitoring and remote warning system includes a plurality of pressure sensors disposed in the patient's bed in a series of rectangular strips or zones that run laterally across the bed in the area of the patient's mid-back, hips and mid-legs, respectively. Each zone contains a plurality of sensors, arranged symmetrically about the centerline of the bed, with the corresponding sensors on opposite sides of the centerline in each zone being connected in parallel. The sensors are connected to a processor with multiple input channels that continuously monitors the sensor states to determine, from the pattern of sensor states observed, whether the patient is in bed, out of bed or is actively attempting to ext the bed at the sides or foot of the bed. At least three different sets of bed exit logic rules are available for user selection to configure the system for high, medium or low sensitivity, or bed exit privileges, for any particular patient. In some embodiments, the system also is capable of detecting when a patient is attempting to assume certain prohibited in-bed positions, such as sitting positions or slumping positions. An alarm in the form of a pre-recorded voice announcement or an alarm over a pre-existing nurse call system is provided when the sensor states are indicative of an out-of-bed or an exiting bed condition, or other prohibited in-bed positions, for a predetermined minimum period of time.
Owner:HOANA MEDICAL

End-to-end identification method for scene text with random shape

The invention discloses an end-to-end identification method for a scene text with a random shape. The method comprises the steps of extracting a text characteristic through a characteristic pyramid network for generating a candidate text box by an area extracting network; adjusting the position of the candidate text box through quick area classification regression branch for obtaining more accurate position of a text bounding box; inputting the position information of the bounding box into a dividing branch, obtaining a predicated character sequence through a pixel voting algorithm; and finally processing the predicated character sequence through a weighted editing distance algorithm, finding out a most matched word of the predicated character sequence in a given dictionary, thereby obtaining a final text identification result. According to the method of the invention, the scene texts with the random shape can be simultaneously detected and identified, wherein the scene texts comprisehorizontal text, multidirectional text and curved text. Furthermore end-to-end training can be completely performed. Compared with prior art, the identification method according to the invention has advantages of obtaining advantageous effects in accuracy and versatility, and realizing high application value.
Owner:HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products