1. A flexible retroreflective article comprising:
a polymeric light transmissive body layer having an elastic modulus of less than 7\xd7108 pascals;
a plurality of cube-corner elements projecting from a major surface of the body layer; and
a single layer or multilayered seal film adhered to at least portions of the body layer such that the seal film maintains an air interface with the cube-corner elements;
wherein the seal film layer is a thermoplastic polymeric material comprising reaction products of alkylene in an amount of at least about 50% by weight and reaction products of at least one non-acidic comonomer in an amount of less than 25 wt %.
2. The flexible retroreflective article of claim 1, wherein the thermoplastic polymeric material comprises acid modification, anhydride modification, carbon monoxide modification, and combinations thereof.
3. The flexible retroreflective article of claim 1, wherein the alkylene has 2 to 8 carbon atoms.
4. The flexible retroreflective article of claim 3, wherein the alkylene is ethylene.
5. The flexible retroreflective article of claim 1, wherein the non-acidic comonomer is selected from vinyl acetate, alkyl(meth)acrylate monomers, and mixtures thereof.
6. The flexible retroreflective article of claim 5, wherein the alkyl(meth)acrylate monomers have an alkyl group having 1 to 8 carbon atoms.
7. The flexible retroreflective article of claim 5, wherein the alkyl(meth)acrylate monomers are selected from the group consisting of methyl acrylate, methyl methacrylate, ethyl acrylate, ethyl methacrylate, butyl acrylate, butyl methacrylate and mixtures thereof.
8. The flexible retroreflective article of claim 1, wherein the seal film comprises a copolymer or terpolymer of alkylene and at least one non-acid polar comonomer selected from vinyl acetate, alkyl(meth)acrylate monomers, and mixtures thereof.
9. The flexible retroreflective article of claim 8, wherein the copolymer or terpolymer comprises about 10 wt-% to about 40 wt-% of vinyl acetate, alkyl(meth)acrylate monomers, and mixtures thereof.
10. The flexible retroreflective article of claim 1, wherein the seal film includes at least one of EVA copolymers, acid- or anhydride-modified EVA, acid or anhydride-acrylate-modified EVA, ethylene ethyl acrylate copolymers, ethylene methyl acrylate copolymers, acid- or anhydride-modified ethylene acrylate polymers, and EVA carbon monoxide terpolymers.
11. The flexible retroreflective article of claim 1, wherein the seal film comprises a blend of at least two thermoplastic polymers and the blend comprises reaction products of alkylene in an amount of at least about 50% and reaction products of vinyl acetate, alkyl (meth)acrylate monomers, and mixtures thereof.
12. The flexible retroreflective article of claim 11, wherein the blend comprises a thermoplastic polymer selected from ionomeric ethylene compolymers, low density polyethylene, EAA, EMA, and polyurethanes.
13. The flexible retroreflective article of claim 1, wherein the seal film has a melt index of less than 25 g10 min as measured according to ASTM D 1238.
14. The flexible retroreflective article of claim 1, wherein the seal film further comprises at least one pigment, dye, or combination thereof.
15. The flexible retroreflective article of claim 1, wherein the seal film is monolithic.
16. The flexible retroreflective article of claim 1, wherein the seal film is multilayered having a seal film layer disposed between the cube-corner elements and a second film layer.
17. The flexible retroreflective article of claim 16, wherein the second film layer is selected from
a) film compositions that comprises the same thermoplastic polymer composition as claim 1 and further comprise 5 wt-% to 20 wt-% of pigment,
b) film compositions that comprises the same thermoplastic polymer composition as claim 1 and a different melt flow index than the seal film layer, and
c) film compositions that comprise a different thermoplastic polymer composition than claim 1 and optionally include a tie layer between the seal film layer and second film layer.
18. The flexible retroreflective article of claim 1, wherein the seal-film contacts the body layer or cube film at an interface and the interface further comprises an adhesion promoting surface treatment.
19. The flexible retroreflective article of claim 18, wherein the adhesion promoting surface treatment comprises a prime layer, corona treatment, or a combination thereof.
20. The flexible retroreflective article of claim 1, wherein the body layer comprises a polymeric material selected from ionomeric ethylene copolymers, low density polyethylenes, polyethylene copolymers, plasticized poly(vinychloride), polyurethane, and mixtures thereof.
21. The flexible retroreflective article of claim 1, wherein the body layer is olefinic.
22. A retroreflective article that comprises:
a plurality of cube-corner elements; and
a seal film layer adhered to portions of the cube-corner elements such that the seal film layer maintains an air interface with the cube-corner elements;
wherein the seal film layer is a thermoplastic polymeric material comprising reaction products of alkylene in an amount of at least about 50% by weight and reaction products of at least one non-acidic comonomer in an amount of less than 25 wt %.
23. The retroreflective article of claim 22, wherein the cube-corner elements project from an integral body layer.
24. The retroreflective article of claim 22, wherein the cube-corner elements comprise a thermoplastic polymeric material.
25. The retroreflective article of claim 22, wherein the cube-corner elements comprise the reaction product of a polymerizable resin composition.
26. The retroreflective article of claim 22, wherein the cube-corner elements comprise at least one nitrogen-containing ingredient.
27. A microstructured article that comprising
a plurality of microstructured elements; and
a seal film adhered to portions of the cube-corner elements such that the seal film maintains an air interface with the microstructured elements;
wherein the seal film layer is a thermoplastic polymeric material comprising reaction products of alkylene in an amount of at least about 50% by weight and reaction products of at least one non-acidic comonomer in an amount of less than 25 wt %.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. A detection device for detecting a plurality of classes of object data, comprising:
an input unit, configured to input data to be detected; and
a joint classifier comprising strong classifiers, the number of which corresponds to the number of the classes and which are used for detecting a corresponding class of the object data respectively, wherein each of the strong classifiers is obtained from a combination of a group of weak classifiers, and each of the weak classifier performs a weak classification on the data to be detected using a feature,
wherein the joint classifier comprises a shared features list, and each feature in the shared features list is shared by one or more weak classifiers respectively belonging to different strong classifiers; and the weak classifiers using a same feature and belonging to different strong classifiers have parameter values different from one another.
2. The detection device according to claim 1, further comprising a judgment unit configured to judge which class of the object data the data to be detected belongs to based on classification results of the plurality of strong classifiers.
3. A detection device for detecting a plurality of classes of object data, wherein the plurality of classes are merged step-by-step into a predetermined multilayer structure according to a similarity criterion and arranged at a bottom layer as the most finely classified classes, and the detection device comprises:
an input unit, configured to input data to be detected; and
a cascade classifier comprising a plurality of level classifiers connected in series, the plurality of level classifiers being configured to perform a classification respectively on the classes at respective layers in the predetermined multilayer structure according to a from-coarse-to-fine policy and each of the level classifiers comprising strong classifiers, the number of which corresponds to the number of the classes being classified, wherein each of the strong classifiers comprises a group of weak classifiers, and each of the weak classifiers performs a weak classification on the data to be detected using a feature,
wherein each of the level classifiers comprises a shared features list, and each feature in the shared features list is shared by one or more weak classifiers respectively belonging to different strong classifiers; and the weak classifiers using a same feature and belonging to different strong classifiers have parameter values different from one another.
4. The detection device according to claim 3, wherein each of the level classifiers is further configured to calculate feature values of respective valid features in the shared feature list for the input data to be detected, and to query, for each of the strong classifiers in the level classifier, the a feature values list obtained from calculation according to the features used for the strong classifier to thereby determine and sum up outputs of the respective weak classifiers of the strong classifier to obtain a final output of the strong classifier.
5. The detection device according to claim 3, wherein the cascade classifier is configured to subject the input data to be detected sequentially to judgment by the respective strong classifiers in the respective level classifiers so that if the input data to be detected is judged by one of the strong classifiers for detection of the class Ci as non-object data, then the input data to be detected is no longer judged by the corresponding strong classifiers for detection of the class Ci andor sub-classes thereof in the subsequent respective level classifiers.
6. The detection device according to claim 5, wherein the cascade classifier is configured to judge, for each of the level classifiers, whether there is a feature in the shared features list, which is correlated only with the respective strong classifiers precluded from the judgment process, and label the feature if any as an invalid feature for which no feature value is further calculated.
7. The detection device according to claim 3, wherein the cascade classifier is configured to terminate the classification and judge the data to be detected as non-object data if the data to be detected is rejected by all of the strong classifiers in any one of the level classifiers.
8. The detection device according to claim 3, wherein the last one of the level classifiers further comprises a judgment unit configured to judge the data to be detected as having an object-class-attribute corresponding to a certain strong classifier if the data to be detected is passed by the strong classifier, and to judge the data to be detected as having a corresponding multi-object-class-attribute if the data to be detected is passed by the plurality of strong classifiers of the last one of the level classifier.
9. The detection device according to claim 3, which is used for detecting a plurality of class of a predetermined object in an input image or video, further comprising a window traversal component configured to perform window-traversal on an image to be detected or an image intercepted from an video to be detected, and
the cascade classifier is configured to perform a classification on a window image acquired by the window traversal component and to record the position and the size of the window in an original image and all the object-class-attributes thereof in the case that the window image is judged as an object class.
10-11. (canceled)
12. A detection method for detecting a plurality of classes of object data, comprising:
inputting data to be detected; and
performing a classification on the data to be detected using a joint classifier comprising a plurality of strong classifiers, wherein the number of the strong classifiers corresponds to the number of the classes and the strong classifiers are respectively used for detecting a corresponding class of the object data; the joint classifier comprises a shared features list, and each feature in the shared features list is shared by one or more weak classifiers respectively belonging to different strong classifiers; and the weak classifiers using a same feature and belonging to different strong classifiers have parameter values different from one another.
13. The detection method according to claim 12, further comprising judging which class of the object data the data to be detected belongs to based on classification results of the plurality of strong classifiers.
14. A detection method for detecting a plurality of classes of object data, wherein the plurality of classes are merged step-by-step into a predetermined multilayer structure according to a similarity criterion and arranged at a bottom layer as the most finely classified classes, and the detection method comprises:
inputting data to be detected; and
perform a classification on the data to be detected with a cascade classifier comprising a plurality of level classifiers connected in series, wherein the plurality of level classifiers are configured to perform a classification respectively on the classes at respective layers in the predetermined multilayer structure according to a from-coarse-to-fine policy and each of the level classifiers comprises strong classifiers, the number of which corresponds to the number of the classes being classified; and
wherein the step of performing a classification with the cascade classifier comprises subjecting the input data to be detected sequentially to judgment by the respective strong classifiers in the respective level classifiers, wherein each of the level classifiers comprises a shared features list, and each feature in the shared features list is shared by one or more weak classifiers respectively belonging to different strong classifiers; and the weak classifiers using a same feature and belonging to different strong classifiers have parameter values different from one another.
15. The detection method according to claim 14, wherein the step of subjecting the input data to be detected sequentially to judgment by the respective strong classifiers in each of the level classifiers comprises:
for the input data to be detected, calculating feature values of respective valid features in the shared features list of the level classifier; and for each of the strong classifiers in the level classifier, querying a feature values list obtained from calculation according to the features used for the strong classifier to thereby determine and sum up outputs of the respective weak classifiers of the strong classifier to obtain a final output of the strong classifier.
16. The detection method according to claim 14, wherein the step of subjecting the input data to be detected sequentially to judgment by the respective strong classifiers in the respective level classifiers comprises: if the input data to be detected is judged by one of the strong classifiers for detection of the class Ci as non-object data, then the input data to be detected no longer being judged by the corresponding strong classifiers for detection of the class Ci andor sub-classes thereof in the subsequent respective level classifiers.
17. The detection method according to claim 16, wherein the step of subjecting the input data to be detected sequentially to judgment by the respective strong classifiers in each of the level classifiers comprises: judging whether there is a feature in the shared features list of the level classifier, which is correlated only with the respective strong classifiers precluded from the judgment process, and labeling the feature if any as an invalid feature for which no feature value is further calculated.
18. The detection method according to claim 14, wherein the step of performing a classification with the cascade classifier further comprises: terminating the classification and judging the data to be detected as non-object data if the data to be detected is rejected by all of the strong classifiers in any one of the level classifiers.
19. The detection method according to claim 14, further comprising: after classification with the last one of the level classifier,
judging the data to be detected as having an object-class-attribute corresponding to a certain strong classifier if the data to be detected is passed by the strong classifier; and judging the data to be detected as having a corresponding multi-object-class-attribute if the data to be detected is passed by the plurality of strong classifiers of the last one of the level classifier.
20. The detection method according to claim 14, which is used for detecting a plurality of class of a predetermined object in an input image or video, further comprising: performing a window-traversal on an image to be detected or an image intercepted from a video to be detected, and
the step of performing a classification on the data to be detected with the cascade classifier comprising: perform a classification on a window image acquired by the window-traversal with the cascade classifier and recording the position and the size of the window in an original image and all the object-class-attributes thereof in the case that the window image is judged as an object class.
21. The detection method according to claim 20, further comprising: merging the windows in the local vicinity with the object-class-attributes generated by the window traversal component.
22. The detection method according to claim 21, wherein the step of merging the windows in the local vicinity comprises:
for the windows with an adjacent position of window center, a similar size scaling and the same object-class-attributes, calculating the average central position and the average window size of a cluster of object windows in the vicinity, and taking the number of merged windows as a confidence of the result of merging;
merging the object attributes of the results of merging with an adjacent central position and a similar size after merging, wherein if there are a plurality of results of merging with different object attributes in the vicinity of a certain position in the image, then the sum of confidence of the respective object attributes are calculated, one of the object attributes with the largest sum of confidences is taken as a final object attribute, and the sum of the sums of confidence of the respective object attributes is taken as a confidence of the final result of merging; and
if the confidence of the final result of merging is above or equal to a preset threshold of confidence, then accepting the final result of merging; otherwise, discarding the final result of merging.