Automatic perception method and device

• US 7,212,669 B2
• Filed: 02/23/2001
• Issued: 05/01/2007
• Est. Priority Date: 02/24/2000
• Status: Expired due to Fees

• Current Assignee: Image Processing Technologies, LLC (General Patent Corporation), William J. Brown
• Original Assignee: William J. Brown
• Inventors: Pirim, Patrick
• Primary Examiner(s): Chen; Wenpeng
• Assistant Examiner(s): Ge; Yuzhen
• Application Number:
  US10/204,825
• Publication Number:
  US 20030152267A1
• Time in Patent Office: 2,258 Days
• Field of Search: 382/170
• US Class Current: 382/170
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 7/41 based on statistical description of texture

Abstract

The invention concerns a method and a device for the automatic perception of an event. Said device comprises a control unit, a data bus, a back-annotation bus and at least a histogram computing unit.

Claims

1. An automatic visual perception device for an even occurring in a space with respect to at least one digitized parameter, comprising at least two histogram calculation units for the treatment of the at least one parameter a control unit, a data bus, a time coincidences bus carrying at least a time coincidences signal, the histogram calculation unit being configured to form a histogram representative of the parameter in function of a validation signal and to determine by classification a binary classification signal resulting from the comparison of the parameter and a selection criterion C, wherein the classification signal is sent to the time coincidences bus, and wherein the validation signal is produced from time coincidences signals from the time coincidence bus so that the calculation of the histogram depends on the classification signals carried by the time coincidence bus, and

wherein the histogram calculation units process data a_ijt associated with pixels forming together a multidimensional space (i,j) evolving with the course of time and represented at a succession of instants (T), wherein said data reaches said calculation unit in the form of a digital signal DATA(A) in the form of a succession a_ijt of binary numbers of n bits associated with synchronization signals enabling to define the given instant (T) of the space and the position (i,j) of the pixel in this space, to which the signal a_ijt received at a given instant (T) is associated, said unit comprising:

an analysis memory including a memory with addresses, each address associated with possible values of the number of n bits of the signal DATA(A) and whose writing process is controlled by a WRITE signal;

a classifier comprising a memory intended for receiving a selection criterion C of the parameter DATA(A), said classifier receiving the signal DATA(A) at the input and outputting a binary output signal whereof the value depends on the result of the comparison of the signal DATA (A) with the selection criterion C,

a time coincidences unit that receives signals from the time coincidence bus, said time coincidences unit outputs a positive global enabling signal when the time coincidences signals are valid,

a test unit,

an analysis output unit,

an address multiplexer,

an incrementation enabling unit wherein the counter of each address in the memory corresponds to the value (d) of a_ijt at a given instant, which is incremented by one unit when the time coincidences unit outputs a positive global, enabling signal,

the test unit intended for calculating and storing statistical data processes, after receiving the data a_ijt corresponding to the space at an instant (T), the content of the memory in order to update the analysis output unit,

wherein the memory is deleted before the beginning of each frame for a space at an instant (T) by an initialization signal “

INIT”

, and wherein;

the memory of the classifier is an addressable memory enabling real time updating of the selection criterion (C) and having a data input DATA IN, an address command ADDRESS and a writing command WR, receiving on its input the output from the analysis memory and a signal END on its writing command,

the histogram processing units further comprise a data input multiplexer with two inputs and one output, receiving on one of its inputs a counting signal COUNTER and on its other input, the succession of data a_ijt and outputting the succession of data a_ijt to the address command of the memory of the classifier and an operator OR controlling the address multiplexer and receiving on its inputs an initialization signal INIT and the end signal END.

2. An automatic visual perception device according to claim 1, further comprising, to process several parameters, several histogram calculation units organized into a matrix, wherein each of the calculation units is connected to the data and time coincidences buses.

3. An automatic visual perception device according to claim 1, wherein the space (i,j) is two-dimensional and in that the signal DATA(A) is associated with the pixels of a succession of images.

4. An automatic visual perception device according to claim 1, wherein the histogram processing units comprise means for anticipating the value of the classification criterion (C).

5. An automatic visual perception device according to claim 4, wherein the means for anticipating the value of the classification criterion (C) comprise memories intended for containing the values of statistical parameters relating to two successive frames (T₀ and T₁).

6. An automatic visual perception device according to claim 5, wherein the statistical parameters are the average values of the data a_ijt enabled.

7. An automatic visual perception device according to claim 1, wherein the analysis output register of the histogram calculation units constitutes and stores in its memory at least one of the following values:

the minimum ‘

MIN’

, the maximum ‘

MAX’

, the maximum number of pixels for which the signal V_ijt has a particular value ‘

RMAX’

, the particular value corresponding POSRMAX, and the total number of enabled pixels ‘

NBPTS’

.

8. An automatic visual perception device according to claim 1, wherein the statistical comparison parameter used by the classifier is RMAX/2.

9. An automatic visual perception device according to claim 1, further comprising a controlled multiplexer, configured to receive at input several statistical parameters and in that the comparison made by the classifier depends on a command issued by this multiplexer.

10. An automatic visual perception device according to claim 1, wherein in certain histogram calculation units, at least, a learning multiplexer configured to receive an external command signal and to initiate an operation according to a learning mode wherein the registers of the classifier and of the time coincidences unit are erased when starting to process a frame, and wherein the analysis output register supplies values typical of the sequence of each of these registers.

11. An automatic visual perception device according to claim 1, wherein in certain histogram calculation units, at least the memory of the classifier includes a set of independent registers (D), each comprising one input, one output and one writing command, wherein the number of these registers (D) is equal to the number n of bits of the numbers of the succession V_ijt, and in that it comprises a decoder configured to output a writing command signal corresponding to the related input value (address) and a multiplexer controlled by this input value, thus enabling to read the chosen register.

12. An automatic visual perception device according to claim 1, wherein certain histogram calculation units at least, comprise multiplexers, one of them being associated with the input of each register, and combinatory modules connecting the registers to one another, wherein the multiplexers are configured to choose between a sequential writing mode and a writing mode common to all registers connected together by the combinatory modules.

13. An automatic visual perception device according to claim 12, wherein in certain histogram calculation units at least, the combinatory modules comprise a morphological expansion operator including a three-input logic unit ‘

OR’

, wherein the first input unit receives the output signal of the ‘

Q’

-order register, wherein the second input unit is connected to the output of a two-input logic unit ‘

AND’

receiving respectively the output signal of the ‘

Q+1’

-order register and a positive expansion signal, and wherein the third input unit is connected to the output of a two-input logic unit ‘

AND’

receiving respectively the output signal of the ‘

Q−

1’

-order register and a negative expansion signal.

14. An automatic visual perception device according to claim 13, wherein in certain histogram calculation units at least, the combinatory modules comprise a morphological erosion operator including a three-input logic unit ‘

AND’

, wherein the first input unit receives the output signal of the ‘

Q’

-order register, wherein the second input unit is connected to the output of a logic unit ‘

AND’

, wherein one four-input reverse receives respectively the output signal of the ‘

Q’

-order register, the output signal of the ‘

Q−

1’

-order register, the output signal of the ‘

Q+1’

-order register and a positive erosion signal, and wherein the third input unit is connected to the output of a four-input logic unit ‘

AND’

, wherein one reverse receives respectively the output signal of the ‘

Q’

-order register, the output signal of the ‘

Q−

1’

-order register, the output signal of the ‘

Q+1’

-order register and a negative erosion signal.

15. An automatic visual perception device according to any of the claims 13 and claim 14, wherein in certain histogram calculation units at least, each combinatory module comprises a multiplexer associating a morphological expansion operator and a morphological erosion operator.

16. Histogram calculation unit as implemented in the automatic visual perception device according to claim 1.

17. A method for automatic perception of an event occurring in a space with respect to at least one parameter, comprising digitizing the parameter, characterized in that said parameter is transmitted under control of a control unit via a data bus to at least one histogram calculation unit, the histogram calculation unit calculating a histogram representative of the parameter as a function of a validation signal and determining by classification a binary classification signal resulting form the comparison of the parameter and a selection criterion C, wherein the classification signal is sent to a time coincidences bus, wherein the classification signals of the time coincidences bus are used to generate the validation signal in order to make the calculation of the histogram depend on the classification signals carried by the time coincidence bus, and

calculating a histogram over data a_ijt associated with pixels forming together a multidimensional space (i,j) evolving with the course of time and represented at a succession of instants (T), wherein said data reaches said calculation unit in the form of a digital signal DATA(A) in the form of a succession a_ijt of binary number of n bits associated with synchronization signals enabling to define the given instant (T) of the space and the position of the pixel (i,j) in this space, to which the signal a_ijt received at a given instant (t) is associated, wherein:

to each data a_ijt is associated a classification binary signal whereof the value depends on the result of the comparison between the signal DATA(A) and the selection criterion C,

a statistical distribution of the data a_ijt is made for a given instant (T) for which a global enabling signal is positive, said global enabling signal being made of a set of individual time coincidences signals, each one corresponding to a parameter DATA(A), DATA (B), . . . , DATA(E), resulting from the comparison between a time coincidences criterion R and the classification signal and being positive.

18. A method according to claim 17, wherein the event is represented by several parameters and wherein the result is derived from several histogram calculation units organized into a matrix, wherein each of the calculation units is connected to the data and times coincidences buses.

19. A method for analyzing a parameter according to claim 17, wherein the space (i,j) is two-dimensional and in that the signal DATA(A) is associated with the pixels of a succession of images.

20. An analysis method of a parameter according to claim 19, wherein updating the classification criterion (C) is anticipated.

21. An analysis method of a parameter according to claim 20, wherein anticipating the update of the classification criterion (C) results from successive applications of an expansion operator and of an erosion operator, each of them, a number of times and in a direction depending on the evolution of the average of the parameter a_ijt validated between two successive frames (T₀ and T₁).

22. An analysis method of a parameter according to claim 17, wherein the classification criterion (C) is updated, in real time, in relation to the statistical distribution.

23. An analysis method of a parameter according to claim 22, wherein updating the classification criterion (C) depends on the evolution of the average of the parameter a_ijt enables between two successive frames (T₀ and T₁).

24. An analysis method of a parameter according to claim 17, wherein the time coincidences criterion (R) is complex.

25. An analysis method of a parameter according to claim 17, wherein the coincidences criterion (R) is automatically proposed next to a learning step.