Mode decision using approximate ½ pel interpolation

1. A method for encoding a video signal, comprising the steps of:

(A) generating first sub-pel data used in at least one of (i) a motion estimation and (ii) a mode decision by first filtering reference data;

(B) generating second sub-pel data used in a motion compensation by second filtering said reference data, wherein

(i) said first filtering utilizes a first number of a plurality of non-zero taps,

(ii) said second filtering utilizes a second number of said non-zero taps and

(iii) said first number is less than said second number;

(C) generating third sub-pel data used in said mode decision by third filtering of said reference data, wherein a performance of said third filtering is different than both said first filtering and said second filtering,

wherein said first filtering, said second filtering and said third filtering are performed in parallel; and

(D) compressing said video signal by inter-coding based on said motion estimation.

2. The method according to claim 1 , wherein a performance of said second filtering matches third filtering used in said motion compensation in a video decoder to minimize drift.

3. The method according to claim 1 , wherein said first filtering and said second filtering are performed in parallel.

4. The method according to claim 1 , wherein a first sub-pel resolution of said first filtering used in said motion estimation matches a second sub-pel resolution of said second filtering used in said motion compensation.

5. The method according to claim 1 , wherein said first sub-pel data is used in both (i) said motion estimation and (ii) said mode decision.

6. The method according to claim 1 , further comprising the step of:

starting an integer pel search before generating said first sub-pel data used in said motion estimation.

7. The method according to claim 1 , wherein a resolution of said first filtering used in said motion estimation comprises a half-pel resolution.

8. The method according to claim 1 , further comprising the step of:

generating an encoded bitstream compliant with at least one of an International Organization for Standardization/International Electrotechnical Commission 14496-10 standard and an International Telecommunication Union-Telecommunications Standardization Sector Recommendation H.264.

9. An encoder circuit comprising:

at least one processor configured to

(i) generate first sub-pel data used in at least one of (a) a motion estimation and (b) a mode decision by first filtering reference data,

(ii) generate second sub-pel data used in a motion compensation by second filtering said reference data and

(iii) compress a video signal by inter-coding based on said motion estimation, wherein

(i) said first filtering utilizes a first number of a plurality of non-zero taps,

(ii) said second filtering utilizes a second number of said non-zero taps and

(iii) said first number is less than said second number,

wherein (i) said mode decision uses a third sub-pel data generated by third filtering said reference data and (ii) a performance of said third filtering is different than both said first filtering and said second filtering,

wherein said first filtering, said second filtering and said third filtering are performed in parallel.

10. The encoder circuit according to claim 9 , wherein a performance of said second filtering matches third filtering used in said motion compensation in a video decoder to minimize drift.

11. The encoder circuit according to claim 9 , wherein said first number is no greater than two of said non-zero taps.

12. The encoder circuit according to claim 9 , wherein said first number is no greater than four of said non-zero taps.

13. The encoder circuit according to claim 9 , wherein said first sub-pel data used in said mode decision comprises half-pel data.

14. The encoder circuit according to claim 9 , wherein said second number is at least six of said non-zero taps.

15. A circuit for video encoding comprising:

means for generating first sub-pel data used in at least one of (i) a motion estimation and (ii) a mode decision by first filtering reference data;

means for generating second sub-pel data used in a motion compensation by second filtering said reference data, wherein (i) said first filtering utilizes a first number of a plurality of non-zero taps, (ii) said second filtering utilizes a second number of said non-zero taps and (iii) said first number is less than said second number;

means for generating third sub-pel data used in said mode decision by third filtering of said reference data, wherein a performance of said third filtering is different than both said first filtering and said second filtering,

wherein said first filtering, said second filtering and said third filtering are performed in parallel; and

means for compressing a video signal by inter-coding based on said motion estimation.

16. The method according to claim 1 , wherein said second number is at least six of said non-zero taps.