Recycling methods and systems, and related plastic containers
A plastic item, such as a beverage bottle, conveys two distinct digital watermarks, encoded using two distinct signaling protocols. A first, printed label watermark conveys a retailing payload, including a Global Trade Item Number (GTIN) used by a point-of-sale scanner in a retail store to identify and price the item when presented for checkout. A second, plastic texture watermark conveys a recycling payload, including data identifying the composition of the plastic. The use of two different signaling protocols assures that a point-of-sale scanner will not spend its limited time and computational resources working to decode the recycling watermark, which lacks the data needed for retail checkout. In some embodiments, a recycling apparatus makes advantageous use of both types of watermarks to identify the plastic composition of the item (e.g., relating GTIN to plastic type using an associated database), thereby increasing the fraction of items that are correctly identified for sorting and recycling. A great number of other features and arrangements are also detailed.
1. A recycling method that includes the acts of:
capturing imagery depicting items in a material stream;
extracting first digital watermark payload data, comprising plural symbols, from imagery depicting a first item in said material stream and, based on the first digital watermark payload, determining that the first item is made with a first type of plastic;
extracting second digital watermark payload data comprising plural symbols, from imagery depicting a second item in said material stream and, based on the second digital watermark payload data, determining that the second item is made with a second type of plastic; and
sorting said first and second items from the material stream based on said determined types of plastic; wherein the captured imagery comprises image frames, each frame comprising plural pixel blocks and each pixel block comprising plural sub-blocks, and the method further includes the acts of:
analyzing pixel blocks in image frames to detect a clue suggesting presence of watermark data in said pixel blocks, and undertaking further image analysis of pixel blocks in which a clue was detected, wherein the first digital watermark payload data is extracted as a consequence of finding a first clue, and the second digital watermark payload data is extracted as a consequence of finding a second clue; and
detection of the first clue includes (a) computing, for each of the plural sub-blocks in a pixel block, an average value of pixels in the sub-block, to thereby yield plural sub-block average values for said pixel block, and (b) determining whether a majority of said average values for the pixel block is within 1, 2, 3 or 4 digital values of a peak value of a histogram of average values for said pixel block computed from plural previous frames.
2. The method of claim 1 in which the first type of plastic is polyethylene terephthalate, and the second type of plastic is high-density polyethylene.
3. The method of claim 1 that includes extracting the first digital watermark payload data from imagery depicting a label on the first item.
4. The method of claim 1 that includes extracting the second digital watermark payload data from imagery depicting a 3D surface texture on the second item.
5. The method of claim 1 in which the first digital watermark payload data extracted from the depiction of the first item includes a fixed message portion and a variable message portion, and said variable message portion includes plural fields, wherein one of said fields is a global trade item number (GTIN) field.
6. The method of claim 1 in which the first watermark payload data includes a code identifying a plastic used in the first item, and the second digital watermark payload data includes linking data, wherein the method further includes obtaining a code identifying a plastic used in the second item from a database, through use of said linking data.
7. The method of claim 1 in which the first clue comprises an output from a classifier indicating that a pixel block likely depicts a plastic item.
8. The method of claim 1 in which the first clue comprises an output from a classifier indicating that a pixel block likely does not depict a conveyor belt.
9. The method of claim 1 in which the material stream is moved by a conveyor belt past a camera, wherein items on the conveyor belt enter a camera frame field of view along a first edge of the camera frame, and the method includes analyzing plural overlapping blocks spanning said first edge of the camera frame for clues indicating possible presence of watermark data, and undertaking further image analysis, including searching for a digital watermark orientation signal, after a clue is found.
10. The method of claim 1 in which the first digital watermark is a watermark encoded according to a signaling protocol that represents payload data using a tile of 128×128 elements, and in which the second digital watermark is a watermark encoded according to a second, different, signaling protocol, which represents payload data using a tile of N×N elements, where N<128.
11. The method of claim 1 that includes:
assessing first and second pixel patches in the captured imagery to determine whether said patches likely depict a conveyor belt;
watermark-processing the first pixel patch as a consequence of said assessing determining the first pixel patch likely does-not depict the conveyor belt; and
not watermark-processing the second pixel patch as a consequence of said assessing determining that the second pixel patch likely does depict the conveyor belt;
wherein the first digital watermark is extracted from imagery comprising the first pixel patch.
12. The method of claim 1 that includes illuminating a first region of the material stream with a first illumination source, and illuminating a second region of the material stream with a second illumination source of a type different than the first illumination source, wherein the first digital watermark is extracted from depiction of the first item captured when illuminated by the first illumination source, and the second digital watermark is extracted from depiction of the second item captured when illuminated by the second illumination source.
13. The method of claim 1 in which extracting the first digital watermark payload includes:
determining first affine parameters characterizing pose of the first item as depicted in the first imagery by an iterative process started with a first initial set of affine parameters, and thereafter employing said determined first affine parameters in extracting the first digital watermark payload data; and
determining second affine parameters characterizing pose of the second item as depicted in the second imagery by an iterative process started with a second initial set of affine parameters different than said first initial set, and thereafter employing said determined second affine parameters in extracting the second digital watermark payload data.
14. The method of claim 1 in which the material stream is moved by a conveyor belt at a speed, and the captured imagery comprises an image sequence captured at a frame rate, the sequence including first, second and third frames, the method includes the acts:
analyzing plural image blocks in the first frame for a watermark clue;
detecting a watermark clue in a first image block of the first frame; and
identifying, in the second frame, one or more second image blocks for analysis based on said conveyor belt speed and said frame rate.
15. The method of claim 1 in which the first digital watermark includes a first reference signal and the second digital watermark includes a second reference signal, wherein the first reference signal has a correlation 0.2>r>−0.2, when confusion-tested with the second reference signal over a full range of affine transformations, namely with scales of the first reference signal ranging between 0.5 and 2.0 in increments of 0.02, and with rotations of the first reference signal ranging between
−90 degrees through +90 degrees in increments of 1 degree, and with translations of the first reference signal ranging across every pixel of possible relative translation.
16. The method of claim 1 in which one of said digital watermarks comprises a traveling salesman line path that visits a hundred or more points, once only, and changes direction at a majority of said points.
17. The method of claim 1 in which in which one of said digital watermarks comprises a pattern of multiple curved segments, plural of which are compound-curved with multiple turns along their length, in which some segments cross others, while other segments do not cross others.
18. The method of claim 1 in which each of said first and second items is marked with two different types of watermarks, namely (a) a first type of watermark printed on either the item or on a label applied to the item, said first type of watermark employing a first signaling protocol, and (b) a second type of watermark formed as a 3D texture in the surface of the item, said second type of watermark employing a second signaling protocol different than the first signaling protocol;
wherein the method includes applying first and second different watermark reading algorithms to the captured imagery, the first watermark reading algorithm being adapted to read watermarks employing the first signaling protocol, and the second watermark reading algorithm being adapted to read watermarks employing the second signaling protocol;
wherein the method can sort the first and second items from the material stream based on either the first or second types of watermarks that mark said items, by payload data extracted by said respective first or second watermark reading algorithms.