### Table 1: Comparison of rover positions determined by a human operator overlaying a rover model on stereo data of the rover and by the localization techniques described in this paper.

1998

"... In PAGE 5: ... However, we have achieved good localization results with this data. Table1 shows the results of localization using the 1A sol is a Martian day techniques described in this paper versus the localiza- tion that was obtained by human operator through overlaying a rover model on the stereo data obtained from imaging the rover from the lander. For sol 42, we have two localization results, one prior to and one after a turn by the rover.... ..."

Cited by 46

### Table 1: Comparison of rover positions determined by a human operator overlaying a rover model on stereo data of the rover and by the localization techniques described in this paper.

2000

"... In PAGE 19: ... However, we have achieved good localization results with this data. Table1 shows the results of localization using the techniques described in this paper versus the localization that was obtained by a human operator through overlaying a rover model on the stereo data obtained from imaging the rover from the lander. For sol 42, we have two localization results, one prior to and one after a turn by the rover.... ..."

Cited by 31

### Table 6.3-3. Stereo Matching Results in Figure 6.3.1 with No Filtering.

1993

### Table 2: Stereo correspondence results

"... In PAGE 4: ... Any points for which the least squares matching solution di- verges, or does not converge fast enough (a threshold of 20 iterations is currently used), are also invalidated, and removed from the set of correspondences. Results from the stereo correspondence, using the above matching strategy, are shown in Table2 . A graphical depic- tion of the nal point correspondences for the image pair is depicted in Figure 4.... ..."

### Table 6.5.3.1 Focused and Defocused Stereo-Matching Results of Figure 6.5.3.1.

1993

### Table 3: Result for the correlation technique applied to the stereo pair in Figure 2.

2000

"... In PAGE 18: ... Figure 2 depicts the result for the best correlation window. Table3 shows the results obtained using our method for di erent parameter settings, and in Figure 3 we present the best result that we have obtained with our method. It has an average error of 0:2639.... In PAGE 18: ... We point out that our method computes the disparity in 100% of the image, and that the the error is signi cantly smaller than the one of the correlation technique. Table3 also shows that our method is rather robust concerning the choice of the parameters. In fact, in most cases the results are better than for the correlation method with optimal window size.... ..."

### Table 3: Result for the correlation technique applied to the stereo pair in Figure 2.

"... In PAGE 18: ... Figure 2 depicts the result for the best correlation window. Table3 shows the results obtained using our method for di erent parameter settings, and in Figure 3 we present the best result that we have obtained with our method. It has an average error of 0:2639.... In PAGE 18: ... We point out that our method computes the disparity in 100% of the image, and that the the error is signi cantly smaller than the one of the correlation technique. Table3 also shows that our method is rather robust concerning the choice of the parameters. In fact, in most cases the results are better than for the correlation method with optimal window size.... ..."

### Table 3: Result for the correlation technique applied to the stereo pair in Figure 2.

"... In PAGE 19: ... Figure 2 depicts the result for the best correlation window. Table3 shows the results obtained using our method for di#1Berent parameter settings, and in Figure 3 we present the best result that wehave obtained with our method. It has an average error of 0:2639.... In PAGE 19: ... We point out that our method computes the disparityin100#25 of the image, and that the the error is signi#1Ccantly smaller than the one of the correlation technique. Table3 also shows that our method is rather robust concerning the choice of the parameters. In fact, in most cases the results are better than for the correlation method with optimal window size.... ..."

### Table 2: Comparisons with state of the art. Comparing accuracy and performance of different dense stereo algorithm in estimating occlusion maps.

in Efficient Dense-Stereo and Novel-view Synthesis for Gaze Manipulation in One-to-one Teleconferencing

2003

"... In PAGE 24: ... Comparative results The misclassification rate and the isolation rate have been mea- sured for all the occlusion maps in fig. 18d-h and the results shown in Table2 . Notice that the three graph-cut algorithms [2, 9, 10] perform comparably well and considerably better than standard three-move DP.... In PAGE 25: ... Thus, these results show that the combination of both an extended occlusion model for correct pixel classification and the enforcement of constraints on occluded areas achieves the best results. Table2 also shows our algorithm being the second fastest, immediately after the very efficient (but poor quality) Cox DP. Further notes on our experimental procedure It must be stressed that the different energy minimization algorithms analysed in this section have been applied to exactly the same cost space, which was computed only once7.... In PAGE 25: ... In contrast to [15], our results re-instate dynamic-programming techniques amongst the most accurate and efficient ones for shape recovery from large-disparity image stereo pairs. Furthermore, Table2 suggests two more occlusion-based error metrics which should be added to the set 7Note that we had to adapt the source code in [10] to read our filtered cost space as input. Then, graph-cut was used for energy minimization only.... ..."

Cited by 5

### Table 9. User Profile Matching Technique of the Systems based on Collaborative Filtering

2001

"... In PAGE 45: ... After this, the common techniques used to compute the similarity between users are explained (the nearest neighbor, clustering and classifiers). Table9 shows the user profile matching techniques used by the different analyzed systems. 10.... ..."

Cited by 3