Top Banner

Click here to load reader

Motion Estimation ECE 569 – Spring 2010 Toan Nguyen Shikhar Upadhaya

Apr 01, 2015



  • Slide 1

Motion Estimation ECE 569 Spring 2010 Toan Nguyen Shikhar Upadhaya Slide 2 Outline What is new with motion estimation Four Step Search and Hexagon Search Algorithms Parallelization strategies Results and discussions Slide 3 What is new with motion estimation? The familiar way Full search Full search is not so efficient Some of the most popular fast search algorithms: Diamond search Hexagon search Three-step search Four-step search Orthogonal search And many more Slide 4 So what is the best? There is a trade-off between the run time and the accuracy. Full search will be most accurate because of exhaustive search, but will require more time Fast search is faster but the accuracy will be reduced because of estimation algorithms. We implemented two of the most popular fast search algorithms for comparison: Four Step Search Hexagon Search Slide 5 Four Step Search Algorithm Step 1: A minimum BDM point is found from a nine-checking points pattern on a 5 x 5 window located at the center of the 15 x 15 searching area. If the minimum BDM point is found at the center of the search window, go to Step 4; otherwise go to Step 2. Step 2: The search window size is maintained in 5 x 5. However, the search pattern will depend on the position of the previous minimum BDM point. If the previous minimum BDM point is located at the corner of the previous search window, five additional checking points as shown in Fig. 2(b) are used. If the previous minimum BDM point is located at the middle of horizontal or vertical axis of the previous search window, three additional checking points as shown in Fig. 2(c) are used. If the minimum BDM point is found at the center of the search window, go to Step 4; otherwise go to Step 3. Step 3: The searching pattern strategy is the same as Step 2, but finally it will go to Step 4. Step 4: The search window is reduced to 3 x 3 as shown in Fig. 2(d) and the direction of the overall motion vector is considered as the minimum BDM point among these nine searching points. Slide 6 Four Step Search Example Slide 7 Hexagon Search Algorithm Step 1: The large hexagon with seven checking points is centered at, the center of a predefined search window in the motion field. If the MBD point is found to be at the center of the hexagon, proceed to Step 3; otherwise, proceed to Step 2. Step 2: With the MBD point in the previous search step as the center, a new large hexagon is formed. Three new candidate points are checked, and the MBD point is again identified. If the MBD point is still the center point of the newly formed hexagon, then go to Step 3; otherwise, repeat this step continuously. Step 3: Switch the search pattern from the large to the small size of the hexagon. The four points covered by the small hexagon are evaluated to compare with the current MBD point. The new MBD point is the final solution of the motion vector. Slide 8 Hexagon Search Example Slide 9 Design Implementation Parallelization is possible by dividing the image into small sub-image partitions. Each thread will work on a sub-image independently using a designed algorithm ( i.e Four step search or Hexagon Search). At the end, the minimum SAD of each sub- image is compared to get the final minimum SAD and avoid local minimum. Slide 10 Implementation Notes Since the number of threads we use is multiple of 2s, if the number of sub-image is not multiple of 2s, we need to pad the image with additional rows and columns and we ignore the results from those extra sub-images. We excluded the time it takes to read a text file and store data into the window and image arrays when we compare the runtime for performance analysis. Slide 11 Simulation Results First we varied the number of threads per block to find the maximal configuration that gives the best run time. 256 threads/block give the best performance. Slide 12 Simulation Results (cont.) The runtime of the serial versions and the parallel versions of different algorithms are collected and compare to see what kind of performance improvement we achieved. We only see the performance improvement when the image size is 256x256 or bigger. Any image of size smaller than this will actually decrease the performance. Slide 13 Simulation Results (cont.) So how much speed up do we get and which algorithm is better, Full Search, Four Step Search, or Hexagon Search? Slide 14 Simulation Results (cont.) Overall performance Full_SerialFull_Parallel4SS_Serial4SS_ParallelHexagon_SerialHexagon_parallel 16X160000.01600.078 32X3200.01600.01500.047 64X640.010.0160.010.0150.010.062 128X1280.020.0160.010.0150.010.062 256X2560.090.0310.020.0160.020.047 512X5120.410.0780.060.0160.060.063 1024X10241.640.2650.2360.0320.220.062 2048X20486.560.9220.870.0470.850.078 4096X409626.293.7193.380.113.30.157 Slide 15 Simulation Results (cont.) Performance comparison between NVIDIA 8400 GS and 9800 GT GPUs. Slide 16 Simulation Results (cont.) Distortion measurement (motion estimation quality). Slide 17 Result Analysis Summary 1. Motion estimation parallel versions performance only improve when image is large (256x256). Smaller image will reduce performance. Larger image ~ greater speedup 2. Fast search algorithms outperform full search algorithm, hence fast. 3. Parallelization on Four Step Search gives a slightly edge improvement over Hexagon Search. 4. The distortion we see on the two fast search algorithms are similar. Slide 18 Result Conclusions Based on the data collected from different algorithms, Four Step Search gives a slightly better performance than Hexagon Search, while the distortion is very similar. Hence, Four Step Search is a better fast search algorithm than Hexagon Search. Only perform motion estimation algorithms on GPU if image size is larger than 256x256. Smaller image size should be ran serially on CPU. Slide 19 Limitations Image and window files are random. Not make use of shared memory Slide 20 Other parallelization strategy After each step, the SAD of the new checking points will be computed. We can parallelize by having threads to compute SADs of all the points in the sub-image. Then after each step complete and the SAD for the new checking points needed, we already have them computed by the threads in previous step. Drawback of this strategy: Not getting a considerable amount of speedup Lots of data transfer between host and device More complicated implementation Slide 21 References Deepak Turaga, Mohamed Alkanhal. "Search Algorithms for Block- Matching in Motion Estimation". ECE - CMU. March 06, 2010. Lai-Man Po, Wing-Chung Ma. A Novel Four-Step Search Algorithm for Fast Block Motion Estimation. JUNE 1996 Xuan Jing, Lap-Pui Chau. "An Efficient Three-Step Search Algorithm for Block Motion Estimation". IEEE TRANSACTIONS ON MULTIMEDIA JUNE 2004: 435-437. Chen Lu, Wang. "Diamond Search Algorithm". ECE, U of Texas. March 06, 2010. Slide 22 Questions?