Harsh environment emergency escape platform and method

Abstract

The present invention relates to a platform and method for emergency avoidance in a harsh environment, the platform comprising: a visual recognition mechanism, including a visualization acquisition device, a face detection device, a ratio analysis device and a signal triggering device; a data fitting mechanism, for fitting a plurality of remaining water body pixels in a received real-time conversion image to obtain one or more water body image areas; a layout recognition mechanism, for sending a water body approaching signal when a water body image area located in the middle area of ​​the real-time conversion image and occupying a number of water body pixels greater than a preset threshold value exists in the one or more water body image areas. The platform and method for emergency avoidance in a harsh environment of the present invention responds promptly and is easy to operate. Since the harsh environment monitoring mechanism is enabled only when the user uses a portable terminal, and targeted identification is performed on whether there is a water area with a wide distribution in the central position in front, excessive waste of power resources is avoided while ensuring safety.

Description

Technical Field

[0001] The present invention relates to the field of portable terminals, and in particular to a platform and method for emergency avoidance in harsh environments. Background Art

[0002] Portable terminals refer to small and light communication terminal devices that can be carried around, such as digital mobile phones and cell phones. Portable terminal communication technologies include SIM cards and GSM and CDMA mobile phones. SIM cards are used to verify user identity and information confidentiality, and provide communication functions. GSM and CDMA mobile phones are carriers of portable terminals.

[0003] The RF circuit in a portable terminal generally refers to the analog RF and intermediate frequency processing circuit of the portable terminal. The RF circuit is roughly divided into three parts: RF transmission circuit, RF receiving circuit and frequency synthesizer. The RF transmission circuit generally includes transmission intermediate frequency modulation, transmission mixing, RF power amplification, bandpass filtering, antenna switch, etc., starting with the module that modulates the TXI / Q signal (transmitting in-phase / quadrature signal) to a higher frequency.

[0004] Currently, when people use portable terminals, they tend to focus too much on the display interface of the portable terminals and pay less attention to the usage environment of the portable terminals. Once there is a large area of ​​water in front of them, such as a river, there will be a danger of falling into the river. If there is sewage, there will be a risk of stepping on sewage or being splashed by sewage. Summary of the invention

[0005] In order to solve the technical problems in related fields, the present invention provides an emergency avoidance platform for harsh environments. When it is monitored that a user is using a portable terminal, it can effectively identify whether there is a harsh water environment on the back of the portable terminal casing, and promptly issue a corresponding voice alarm, thereby preventing the user from accidentally entering harsh environments including rivers, sewage, etc.

[0006] To this end, the present invention needs to have the following two key invention points:

[0007] (1) detecting whether there is a facial object occupying a large imaging area in front of the housing of the portable terminal, and if so, determining that the relevant user is in a state of viewing the portable terminal, thereby triggering detection of a water body on the back of the housing of the corresponding portable terminal;

[0008] (2) When there is a water object near the housing of the portable terminal, a corresponding voice warning operation is performed, so that the user can avoid it in time to prevent accidentally entering a harsh environment such as a river or sewage.

[0009] According to one aspect of the present invention, a harsh environment emergency avoidance platform is provided, the platform comprising:

[0010] A visual recognition mechanism is provided on the portable terminal, and includes a visualization acquisition device, a face detection device, a ratio analysis device and a signal trigger device; the visualization acquisition device is provided in front of the housing of the portable terminal, and is used to perform a real-time image capture operation on the environment in front of the portable terminal to obtain a corresponding real-time captured image; the face detection device is connected to the visualization acquisition device, and is used to identify one or more facial regions in the real-time captured image where one or more facial targets are located based on human facial imaging features; the ratio analysis device is connected to the face detection device, and is used to obtain the area ratio of each of the one or more facial regions occupying the real-time captured image;

[0011] The signal triggering device is connected to the ratio analyzing device, and is used to issue a detection start instruction when the maximum value of the one or more area ratios respectively corresponding to the one or more facial regions exceeds a preset ratio threshold;

[0012] A rear acquisition mechanism is arranged on the back of the casing of the portable terminal and is connected to the signal triggering device, and is used to start the image acquisition operation of the back of the casing at uniform time intervals upon receiving the detection start instruction, so as to obtain the casing background images of each frame corresponding to each time stamp;

[0013] A first processing device, arranged on the integrated circuit board of the portable terminal, connected to the post-acquisition mechanism, for performing geometric correction processing on the housing background picture corresponding to the current timestamp to obtain a corresponding on-site correction image;

[0014] a second processing device, connected to the first processing device, for performing homomorphic filtering on the received on-site corrected image to obtain a corresponding real-time converted image;

[0015] a content analysis device connected to the second processing device, configured to identify each water body pixel in the real-time conversion image based on the water body brightness imaging feature, and perform an isolated pixel deletion operation on each water body pixel in the real-time conversion image to obtain a corresponding plurality of remaining water body pixels;

[0016] a data fitting mechanism, connected to the content mechanical device, for fitting a plurality of remaining water body pixels in the real-time conversion image to obtain more than one water body image region;

[0017] The layout recognition mechanism is connected to the data fitting mechanism and is used to send a water body approaching signal when there is a water body image area located in the middle area of ​​the real-time conversion image and the number of water body pixels occupied is greater than a preset threshold value among the one or more water body image areas.

[0018] According to another aspect of the present invention, a method for emergency avoidance in a harsh environment is also provided, which includes using the harsh environment emergency avoidance platform as described above to effectively identify whether there is a harsh water environment on the back of a portable terminal casing when a user is monitored using the portable terminal.

[0019] The hostile environment emergency avoidance platform and method of the present invention can respond in time and is easy to operate. Since the hostile environment monitoring mechanism is enabled only when the user uses the portable terminal, and targeted identification is performed on whether there is a centrally located and widely distributed water area ahead, excessive power resources are avoided while ensuring safety. DETAILED DESCRIPTION

[0020] The implementation scheme of the harsh environment emergency avoidance platform and method of the present invention will be described in detail below.

[0021] The development of image recognition has gone through three stages: text recognition, digital image processing and recognition, and object recognition. The research on text recognition began in 1950, generally recognizing letters, numbers and symbols, from printed text recognition to handwritten text recognition, and has a wide range of applications.

[0022] The research on digital image processing and recognition began in 1965. Compared with analog images, digital images have great advantages such as easy storage and transmission, compressibility, low distortion during transmission, and easy processing, which provide a strong impetus for the development of image recognition technology. Object recognition mainly refers to the perception and recognition of objects and environments in the three-dimensional world, which belongs to the category of advanced computer vision. It is a research direction based on digital image processing and recognition, combining artificial intelligence, system science and other disciplines. Its research results are widely used in various industrial and detection robots. One of the shortcomings of modern image recognition technology is its poor adaptive performance. Once the target image is polluted by strong noise or the target image has large defects, it often cannot get the ideal result.

[0023] The mathematical essence of image recognition problem belongs to the mapping problem from pattern space to category space. At present, there are three main recognition methods in the development of image recognition: statistical pattern recognition, structural pattern recognition, and fuzzy pattern recognition. Image segmentation is a key technology in image processing. Since the 1970s, its research has a history of several decades and has always been highly valued. So far, thousands of segmentation algorithms have been proposed with the help of various theories, and research in this area is still actively carried out.

[0024] Currently, when people use portable terminals, they tend to focus too much on the display interface of the portable terminals and pay less attention to the usage environment of the portable terminals. Once there is a large area of ​​water in front of them, such as a river, there will be a danger of falling into the river. If there is sewage, there will be a risk of stepping on sewage or being splashed by sewage.

[0025] In order to overcome the above-mentioned deficiencies, the present invention constructs an emergency escape platform and method for harsh environments, which can effectively solve the corresponding technical problems.

[0026] The harsh environment emergency avoidance platform shown in the embodiment of the present invention includes:

[0027] A visual recognition mechanism is provided on the portable terminal, and includes a visualization acquisition device, a face detection device, a ratio analysis device and a signal trigger device; the visualization acquisition device is provided in front of the housing of the portable terminal, and is used to perform a real-time image capture operation on the environment in front of the portable terminal to obtain a corresponding real-time captured image; the face detection device is connected to the visualization acquisition device, and is used to identify one or more facial regions in the real-time captured image where one or more facial targets are located based on human facial imaging features; the ratio analysis device is connected to the face detection device, and is used to obtain the area ratio of each of the one or more facial regions occupying the real-time captured image;

[0028] The signal triggering device is connected to the ratio analyzing device, and is used to issue a detection start instruction when the maximum value of the one or more area ratios respectively corresponding to the one or more facial regions exceeds a preset ratio threshold;

[0029] A rear acquisition mechanism is arranged on the back of the casing of the portable terminal and is connected to the signal triggering device, and is used to start the image acquisition operation of the back of the casing at uniform time intervals upon receiving the detection start instruction, so as to obtain the casing background images of each frame corresponding to each time stamp;

[0030] A first processing device, arranged on the integrated circuit board of the portable terminal, connected to the post-acquisition mechanism, for performing geometric correction processing on the housing background picture corresponding to the current timestamp to obtain a corresponding on-site correction image;

[0031] a second processing device, connected to the first processing device, for performing homomorphic filtering on the received on-site corrected image to obtain a corresponding real-time converted image;

[0032] a content analysis device connected to the second processing device, configured to identify each water body pixel in the real-time conversion image based on the water body brightness imaging feature, and perform an isolated pixel deletion operation on each water body pixel in the real-time conversion image to obtain a corresponding plurality of remaining water body pixels;

[0033] a data fitting mechanism, connected to the content mechanical device, for fitting a plurality of remaining water body pixels in the real-time conversion image to obtain more than one water body image region;

[0034] The layout recognition mechanism is connected to the data fitting mechanism and is used to send a water body approaching signal when there is a water body image area located in the middle area of ​​the real-time conversion image and the number of water body pixels occupied is greater than a preset threshold value among the one or more water body image areas.

[0035] Next, the specific structure of the severe environment emergency escape platform of the present invention will be further described.

[0036] In the adverse environment emergency escape platform:

[0037] The layout recognition mechanism is also used to send a water body away signal when there is no water body image area located in the middle area of ​​the real-time conversion image and the number of water body pixels occupied is greater than a preset number threshold among the one or more water body image areas.

[0038] The harsh environment emergency escape platform may also include:

[0039] A voice playing chip is arranged in the casing of the portable terminal and opposite to the opening in the front of the casing of the portable terminal, connected to the layout recognition mechanism, and is used to play a voice playing file related to the water approaching signal when receiving the water approaching signal.

[0040] In the adverse environment emergency escape platform:

[0041] Based on the water body brightness imaging feature, each water body pixel in the real-time conversion image is identified, and isolated pixel deletion is performed on each water body pixel in the real-time conversion image to obtain a corresponding plurality of remaining water body pixels, including: the water body brightness imaging feature is a brightness value range limited by a preset brightness upper limit value and a preset brightness lower limit value.

[0042] In the adverse environment emergency escape platform:

[0043] Identifying each water body pixel in the real-time conversion image based on the water body brightness imaging feature, and performing isolated pixel deletion on each water body pixel in the real-time conversion image to obtain a corresponding plurality of remaining water body pixels includes: taking pixels in the real-time conversion image whose brightness is within the brightness value range as water body pixels.

[0044] In the adverse environment emergency escape platform:

[0045] Based on the water body brightness imaging characteristics, each water body pixel in the real-time conversion image is identified, and isolated pixel deletion is performed on each water body pixel in the real-time conversion image to obtain a corresponding plurality of remaining water body pixels, including: performing the following processing for each water body pixel: when there are no other water body pixels within a pixel window centered on the water body pixel, the water body pixel is removed as an isolated pixel.

[0046] In the adverse environment emergency escape platform:

[0047] When there are no other water pixels within a pixel window centered on the water pixel, removing the water pixel as an isolated pixel includes: the pixel window is a pixel window of 4 pixels×4 pixels.

[0048] In the adverse environment emergency escape platform:

[0049] The second processing device, the content parsing device, the data fitting mechanism and the layout recognition mechanism are all arranged on an integrated circuit board of the portable terminal;

[0050] The post-capturing mechanism is further configured to interrupt the image capturing operation of the environment on the back side of the casing at uniform time intervals upon receiving the detection interruption instruction.

[0051] In the adverse environment emergency escape platform:

[0052] The signal triggering device is further configured to issue a detection interruption instruction when the maximum value of the one or more area ratios respectively corresponding to the one or more facial regions does not exceed the preset ratio threshold.

[0053] At the same time, in order to overcome the above-mentioned shortcomings, the present invention also constructs a method for emergency avoidance in harsh environments, which includes using the harsh environment emergency avoidance platform as mentioned above to effectively identify whether there is a harsh water environment in the scene behind the portable terminal casing when it is monitored that a user is using the portable terminal.

[0054] In addition, in the harsh environment emergency avoidance platform, the second processing device, the content parsing device, the data fitting mechanism and the layout identification mechanism are SOC chips with different throughputs respectively. The basic content of the SOC definition is mainly in two aspects: one is its composition, and the other is its formation process. The composition of the system-level chip can be a system-level chip control logic module, a microprocessor / microcontroller CPU core module, a digital signal processor DSP module, an embedded memory module, an interface module for communicating with the outside, an analog front-end module containing ADC / DAC, a power supply and power consumption management module. For a wireless SOC, there is also a radio frequency front-end module, a user-defined logic (which can be implemented by FPGA or ASIC) and a micro-electromechanical module. More importantly, a SOC chip is embedded with a basic software (RDOS or COS and other application software) module or a loadable user software, etc.

[0055] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0056] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0057] The embodiments of the present invention are described above, but the present invention is not limited to the above-mentioned specific implementation modes. The above-mentioned specific implementation modes are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, all of which are protected by the present invention.

Claims

1. A harsh environment emergency escape platform, characterized in that: The platform includes: A visual recognition mechanism is provided on the portable terminal, and includes a visualization acquisition device, a face detection device, a ratio analysis device and a signal trigger device; the visualization acquisition device is provided in front of the housing of the portable terminal, and is used to perform a real-time image capture operation on the environment in front of the portable terminal to obtain a corresponding real-time captured image; the face detection device is connected to the visualization acquisition device, and is used to identify one or more facial regions in the real-time captured image where one or more facial targets are located based on human facial imaging features; the ratio analysis device is connected to the face detection device, and is used to obtain the area ratio of each of the one or more facial regions occupying the real-time captured image; The signal triggering device is connected to the ratio analyzing device, and is used to issue a detection start instruction when the maximum value of the one or more area ratios respectively corresponding to the one or more facial regions exceeds a preset ratio threshold; A rear acquisition mechanism is arranged on the back of the casing of the portable terminal and is connected to the signal triggering device, and is used to start the image acquisition operation of the back of the casing at uniform time intervals upon receiving the detection start instruction, so as to obtain the casing background images of each frame corresponding to each time stamp; A first processing device, arranged on the integrated circuit board of the portable terminal, connected to the post-acquisition mechanism, for performing geometric correction processing on the housing background picture corresponding to the current timestamp to obtain a corresponding on-site correction image; a second processing device, connected to the first processing device, for performing homomorphic filtering on the received on-site corrected image to obtain a corresponding real-time converted image; a content analysis device connected to the second processing device, configured to identify each water body pixel in the real-time conversion image based on the water body brightness imaging feature, and perform an isolated pixel deletion operation on each water body pixel in the real-time conversion image to obtain a corresponding plurality of remaining water body pixels; The following processing is performed for each water pixel: when there are no other water pixels in the pixel window centered on the water pixel, the water pixel is removed as an isolated pixel; A data fitting mechanism, connected to the content analysis device, for fitting a plurality of remaining water body pixels in the real-time conversion image to obtain more than one water body image region; The layout recognition mechanism is connected to the data fitting mechanism and is used to send a water body approaching signal when there is a water body image area located in the middle area of ​​the real-time conversion image and the number of water body pixels occupied is greater than a preset threshold value among the one or more water body image areas.

2. The harsh environment emergency escape platform as claimed in claim 1, characterized in that: The layout recognition mechanism is also used to send a water body away signal when there is no water body image area located in the middle area of ​​the real-time conversion image and the number of water body pixels occupied is greater than a preset number threshold among the one or more water body image areas.

3. The harsh environment emergency escape platform as claimed in claim 2, characterized in that: The platform also includes: A voice playing chip is arranged in the casing of the portable terminal and opposite to the opening in the front of the casing of the portable terminal, connected to the layout recognition mechanism, and is used to play a voice playing file related to the water approaching signal when receiving the water approaching signal.

4. The harsh environment emergency escape platform as claimed in claim 3, characterized in that: Based on the water body brightness imaging feature, each water body pixel in the real-time conversion image is identified, and isolated pixel deletion is performed on each water body pixel in the real-time conversion image to obtain a corresponding plurality of remaining water body pixels, including: the water body brightness imaging feature is a brightness value range limited by a preset brightness upper limit value and a preset brightness lower limit value.

5. The harsh environment emergency escape platform as claimed in claim 4, characterized in that: Identifying each water body pixel in the real-time conversion image based on the water body brightness imaging feature, and performing isolated pixel deletion on each water body pixel in the real-time conversion image to obtain a corresponding plurality of remaining water body pixels includes: taking pixels in the real-time conversion image whose brightness is within the brightness value range as water body pixels.

6. The harsh environment emergency escape platform as claimed in claim 5, characterized in that: When there are no other water pixels within a pixel window centered on the water pixel, removing the water pixel as an isolated pixel includes: the pixel window is a pixel window of 4 pixels×4 pixels.

7. The harsh environment emergency escape platform as claimed in claim 6, characterized in that: The second processing device, the content parsing device, the data fitting mechanism and the layout recognition mechanism are all arranged on an integrated circuit board of the portable terminal.

8. The harsh environment emergency escape platform as claimed in claim 7, characterized in that: The signal triggering device is further configured to issue a detection interruption instruction when the maximum value of the one or more area ratios respectively corresponding to the one or more facial regions does not exceed the preset ratio threshold; The rear acquisition mechanism is also used to interrupt the image acquisition operation of the environment on the back side of the casing at uniform time intervals when receiving the detection interruption instruction.

9. A method for emergency avoidance in a harsh environment, the method comprising using the harsh environment emergency avoidance platform as described in any one of claims 1 to 8 to effectively identify whether there is a harsh water environment in the scene behind a housing of a portable terminal when a user is monitored using the portable terminal.