Ex Parte Ebling et al

Patent Trial and Appeal Board

Feb 26, 2016

12922229 (P.T.A.B. Feb. 26, 2016)

UNITED STA TES p A TENT AND TRADEMARK OFFICE
APPLICATION NO. FILING DATE
12/922,229 09/13/2010
278 7590 03/01/2016
MICHAEL J, STRIKER
103 EAST NECK ROAD
HUNTINGTON, NY 11743
FIRST NAMED INVENTOR
Julia Ebling
UNITED STATES DEPARTMENT OF COMMERCE
United States Patent and Trademark Office
Address: COMMISSIONER FOR PATENTS
P.O. Box 1450
Alexandria, Virginia 22313-1450
www .uspto.gov
ATTORNEY DOCKET NO. CONFIRMATION NO.
4917 8966
EXAMINER
REN, ZHUBING
ART UNIT PAPER NUMBER
2483
NOTIFICATION DATE DELIVERY MODE
03/01/2016 ELECTRONIC
Please find below and/or attached an Office communication concerning this application or proceeding.
The time period for reply, if any, is set in the attached communication.
Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the
following e-mail address( es):
striker@strikerlaw.com
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte JULIA EBLING, CHRISTOF KRUEGER,
and JAN KARL W ARZELHAN
Appeal2014-004357
Application 12/922,229 1
Technology Center 2400
Before DEBRA K. STEPHENS, KARA L. SZPONDOWSKI, and
SHARON PENICK, Administrative Patent Judges.
PENICK, Administrative Patent Judge.
DECISION ON APPEAL
This is an appeal under 35 U.S.C. § 134(a) from the Examiner's Final
Rejection of claims 1, 3, 4 and 8-13, which constitute all the claims pending
in this application.2 We have jurisdiction under 35 U.S.C. § 6(b)(l).
We reverse.
1 Appellants identify Robert Bosch GmbH as the Real Party in Interest.
(Appeal Br. 2.)
2 Claims 2 and 5-7 were cancelled. (Appeal Br. 21.)
Appeal2014-004357
Application 12/922,229
Invention
Appellants' invention concerns counting objects in a surveillance
region. When an object passes completely through the counting section of
the surveillance region, an object counter is increased by one counting value.
A surveillance camera records the surveillance region and outputs an image
data stream of the surveillance region. An extraction module extracts
moving image regions from the image data stream. The moving image
regions represent the whole or partial objects to be counted. The evaluation
is carried out on an image-by-image basis, and the object counter is
increased by a partial value for each image evaluated. If an object passes
completely through the counting section, the accumulation of all the partial
values form the counting value. The partial values added to the object
counter in performing image-by-image observations of one object moving
through the counting area thus in total increase the object counter by one.
(Spec. p. 1, 11. 7-15; p. 2, 1. 26-p. 3, 1. 20; p. 4, 11. 8-26; p. 10, 11. 16-18.)
Illustrative claim 1 is reproduced below, with key limitations
emphasized:
1. A device (1) for counting objects in a surveillance
reg10n, compnsmg
a counting module (9), wherein the counting module
includes an object counter that is increased by one counting
value, on average, when one of the objects, as the object to be
counted, completely passes through a counting section ( 6) in a
counting direction ( 4 ), the counting section ( 6) defining a length
that the corresponding object must cover between entering and
exiting a region of an image in order to be counted,
at least one surveillance camera (2) for recording the
surveillance region, wherein the surveillance camera (2) outputs
an image data stream of the surveillance region,
2
Appeal2014-004357
Application 12/922,229
an extraction module (10), including a flow module (11)
for determining an optical flow field having flow vectors for
extracting moving image regions in a current image of the image
data stream, wherein the moving image regions represent the
objects or segments thereof, and
an estimating module ( 14) for estimating a subsection of
the length that the corresponding object to be counted has
covered in the current image depending on the direction of
motion or velocity of the corresponding moving image region;
wherein the counting module (9) increases the object
counter (9) by a partial value for each current image for one of
the moving image regions (3), a direction of motion thereof
corresponding to the counting direction ( 4) and thus representing
a potential object to be counted, or a segment thereof,
wherein the partial value is less than the counting value,
wherein the subsection is estimated by projecting the flow
vectors onto the counting direction (4) and/or the counting
section ( 6), and
wherein a size of the partial value is determined depending
on the subsection covered and/or a size of the segment of the
object to be counted.
Rejections
The Examiner rejects claims 1, 3, 4, 8, and 10-13 under 35 U.S.C.
§ 103(a) as unpatentable over Sato et al. (US 5,574,762 A; Nov. 12, 1996)
("Sato") and Conrad et al. (US 5,465,115 A; Nov. 7, 1995) ("Conrad").
(Final Act. 3-10.)
The Examiner rejects claim 9 under 35 U.S.C. § 103(a) as
unpatentable over Sato, Conrad and Pavlidis et al. (US 2003/0053659 Al;
Mar. 20, 2003). (Final Action 10.)
3
Appeal2014-004357
Application 12/922,229
Issue
Appellants' arguments present us with the following issue:
Did the Examiner err in finding that Conrad discloses the claim
limitation "the counting module (9) increases the object counter ... by a
partial value for each current image for one of the moving image regions
(3)" where "the partial value is less than the counting value"?
We address only this issue, which is dispositive. We do not address
additional, non-dispositive issues raised by Appellants' arguments.
ANALYSIS
The Examiner finds that Sato teaches the method of claim 1, with the
exception of certain limitations taught by Conrad, including the disputed
limitations. (Final Action 5.) Conrad relates to a video traffic monitor for
counting people using video imaging. A window of an image frame is
subdivided into gates, and an analysis of the contents of the gates is
performed in order to detect and count people moving through the window
area in the image frame. (Conrad Abstract, 5:4-- 20.)
The Examiner finds the increase of a counter value by a partial value
to be taught in Conrad's determination of which gates in the window are
occupied, and determining how many people are represented by those
occupied gates. (Final Action 5---6; Answer 10-11.) When a non-integral
number results from that determination, e.g. 2.5, then that result is rounded
up, e.g., from 2.5 to 3. (Conrad 12:55-57.) The Examiner finds this teaches
or suggests the claimed limitation of a partial value added to the counter
value. (Final Action 5---6; Answer 10-11.)
4
Appeal2014-004357
Application 12/922,229
As the Examiner finds, Figure 14 of Conrad shows how the number of
people present in the window of an image frame is determined using "person
blocks." (Answer 11.) Contiguous gates which are occupied are collected
into person blocks. (Answer 11; Conrad 12:18-22.) When a person block is
identified, the width (in gates) of the person block is used to determine how
many people are in the person block. (Conrad 12:38--40.) If the person
block width is greater than MAXPERSONWIDTH, (i.e., is too large for the
person block to be considered one person), the person block width is divided
by MAXPERSONWIDTH to determine how many people should be
counted for that person block. (Answer 11; Conrad 7:62----67, 12:51-57.) If
the result is a fraction, the number of people in the block is rounded up, e.g.
from 2.5 to 3, to give a PERSON_COUNT of 3. (Final Action 6; Answer
11; Conrad 12:55-57.) PERSON_COUNT is used to determine, when a
person block shrinks or disappears, how many people have left the person
block or the size of the person block that has passed through the window.
(Conrad 13:13-23.)
The Examiner finds that the calculation of PERSON_ COUNT by
rounding to an integer teaches the disputed limitation of increasing the
object counter by a partial value, less than a counting value: "the number 0.5
(e.g. partial value as claimed) has been added and determined by how many
gates that have been covered by the moving persons." (Answer 11.)
However, we agree with Appellants that what is described in Conrad does
not teach or suggest increasing an object counter by a partial value for each
current image. (Appeal Br. 15-16.) Conrad's PERSON_COUNT is
calculated anew for each image. (Conrad Fig. 14, 12:38-57.)
PERSON_COUNT for each image is used to determine, how many people
5
Appeal2014-004357
Application 12/922,229
have left the person block or the size of the person block that has passed
through the window. (Conrad 13:13-23.) Only when a calculated
PERSON_COUNT indicates that people have passed through the window,
which may be after several image cycles of scanning person blocks, is an
increment equal to the number of people calculated to have left made in
Conrad's object counter ("People Count"). (Id. at Fig. 15, 12:58-13:34.)
Thus, Conrad does not teach a partial increment for each current image.
Thus, we agree with the Appellants that the Conrad reference does not
teach the disputed limitations of claim 1, commensurately recited in
independent claim 11. Dependent claims 3, 4, 8-10, 12, and 13 include this
limitation due to their dependence from claims 1 and 11, and we likewise do
not sustain the Examiner's rejection of these claims for the reasons discussed
above with respect to claim 1.
DECISION
The decision of the Examiner to reject claims 1, 3, 4, and 8-13 is
reversed.
REVERSED
6